Neel Nanda

Karma: 10,114

My Research Process: Key Mindsets—Truth-Seeking, Prioritisation, Moving Fast

Neel NandaApr 27, 2025, 2:38 PM

9 points

0 comments11 min readLW link

How I Think About My Research Process: Explore, Understand, Distill

Neel NandaApr 26, 2025, 10:31 AM

35 points

4 comments8 min readLW link

Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update #2)

lewis smith, Senthooran Rajamanoharan, Arthur Conmy, CallumMcDougall, Tom Lieberum, János Kramár, Rohin Shah and Neel Nanda

Mar 26, 2025, 7:07 PM

109 points

15 comments29 min readLW link

(deepmindsafetyresearch.medium.com)

Good Research Takes are Not Sufficient for Good Strategic Takes

Neel NandaMar 22, 2025, 10:13 AM

291 points

28 comments4 min readLW link

(www.neelnanda.io)

Takeaways From Our Recent Work on SAE Probing

Josh Engels, Subhash Kantamneni, Senthooran Rajamanoharan and Neel Nanda

Mar 3, 2025, 7:50 PM

30 points

0 comments5 min readLW link

The GDM AGI Safety+Alignment Team is Hiring for Applied Interpretability Research

Arthur Conmy and Neel Nanda

Feb 24, 2025, 2:17 AM

48 points

1 comment7 min readLW link

MATS Applications + Research Directions I’m Currently Excited About

Neel NandaFeb 6, 2025, 11:03 AM

73 points

7 comments8 min readLW link

Learning Multi-Level Features with Matryoshka SAEs

Bart Bussmann, Patrick Leask and Neel Nanda

Dec 19, 2024, 3:59 PM

42 points

6 comments11 min readLW link

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders

Can, Adam Karvonen, Johnny Lin, Curt Tigges, Joseph Bloom, chanind, Yeu-Tong Lau, Eoin Farrell, Arthur Conmy, CallumMcDougall, Kola Ayonrinde, Matthew Wearden, Sam Marks and Neel Nanda

Dec 11, 2024, 6:30 AM

82 points

6 comments2 min readLW link

(www.neuronpedia.org)

Evolutionary prompt optimization for SAE feature visualization

neverix, Daniel Tan, Dmitrii Kharlapenko, Neel Nanda and Arthur Conmy

Nov 14, 2024, 1:06 PM

21 points

0 comments9 min readLW link

SAEs are highly dataset dependent: a case study on the refusal direction

Connor Kissane, robertzk, Neel Nanda and Arthur Conmy

Nov 7, 2024, 5:22 AM

66 points

4 comments14 min readLW link

SAE Probing: What is it good for?

Subhash Kantamneni, Josh Engels, Senthooran Rajamanoharan and Neel Nanda

Nov 1, 2024, 7:23 PM

33 points

0 comments11 min readLW link

Open Source Replication of Anthropic’s Crosscoder paper for model-diffing

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda

Oct 27, 2024, 6:46 PM

47 points

4 comments5 min readLW link

SAE features for refusal and sycophancy steering vectors

neverix, Dmitrii Kharlapenko, Arthur Conmy and Neel Nanda

Oct 12, 2024, 2:54 PM

29 points

4 comments7 min readLW link

Base LLMs refuse too

Connor Kissane, robertzk, Arthur Conmy and Neel Nanda

Sep 29, 2024, 4:04 PM

60 points

20 comments10 min readLW link

Showing SAE Latents Are Not Atomic Using Meta-SAEs

Bart Bussmann, Michael Pearce, Patrick Leask, Joseph Bloom, Lee Sharkey and Neel Nanda

Aug 24, 2024, 12:56 AM

68 points

10 comments20 min readLW link

Calendar feature geometry in GPT-2 layer 8 residual stream SAEs

Patrick Leask, Bart Bussmann and Neel Nanda

Aug 17, 2024, 1:16 AM

53 points

0 comments5 min readLW link

Extracting SAE task features for in-context learning

Dmitrii Kharlapenko, neverix, Neel Nanda and Arthur Conmy

Aug 12, 2024, 8:34 PM

31 points

1 comment9 min readLW link

Self-explaining SAE features

Dmitrii Kharlapenko, neverix, Neel Nanda and Arthur Conmy

Aug 5, 2024, 10:20 PM

60 points

13 comments10 min readLW link

BatchTopK: A Simple Improvement for TopK-SAEs

Bart Bussmann, Patrick Leask and Neel Nanda

Jul 20, 2024, 2:20 AM

59 points

0 comments4 min readLW link