Neel Nanda

Karma: 5,598

I lead the DeepMind mechanistic interpretability team

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

Neel NandaApr 27, 2025, 2:38 PM

30 points

1 comment EA link

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

Neel NandaApr 26, 2025, 10:31 AM

44 points

2 comments EA link

Neel Nanda’s Quick takes

Neel NandaApr 6, 2025, 10:17 PM

8 points

3 comments EA link

Good Research Takes are Not Sufficient for Good Strategic Takes

Neel NandaMar 22, 2025, 10:13 AM

117 points

0 comments EA link

(www.neelnanda.io)

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

Arthur ConmyFeb 25, 2025, 10:38 PM

11 points

0 comments7 min readEA link

MATS Applications + Research Directions I’m Currently Excited About

Neel NandaFeb 6, 2025, 11:03 AM

31 points

3 comments EA link

Concrete open problems in mechanistic interpretability: a technical overview

Neel NandaJul 6, 2023, 11:35 AM

27 points

1 comment29 min readEA link

Concrete Steps to Get Started in Transformer Mechanistic Interpretability

Neel NandaDec 26, 2022, 1:00 PM

18 points

0 comments12 min readEA link

A Barebones Guide to Mechanistic Interpretability Prerequisites

Neel NandaNov 29, 2022, 6:43 PM

54 points

1 comment3 min readEA link

(neelnanda.io)

An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers

Neel NandaOct 18, 2022, 9:23 PM

19 points

0 comments12 min readEA link

(www.neelnanda.io)

Concrete Advice for Forming Inside Views on AI Safety

Neel NandaAug 17, 2022, 11:26 PM

58 points

4 comments10 min readEA link

(www.alignmentforum.org)

Things That Make Me Enjoy Giving Career Advice

Neel NandaJun 17, 2022, 8:49 PM

34 points

3 comments9 min readEA link

How I Formed My Own Views About AI Safety

Neel NandaFeb 27, 2022, 6:52 PM

134 points

12 comments14 min readEA link

(www.neelnanda.io)

Simplify EA Pitches to “Holy Shit, X-Risk”

Neel NandaFeb 11, 2022, 1:57 AM

186 points

82 comments11 min readEA link

(www.neelnanda.io)

My Overview of the AI Alignment Landscape: A Bird’s Eye View

Neel NandaDec 15, 2021, 11:46 PM

45 points

15 comments16 min readEA link

(www.alignmentforum.org)

Optimisation-focused introduction to EA podcast episode

Neel NandaJan 15, 2021, 9:59 AM

8 points

1 comment1 min readEA link

(art19.com)

Retrospective on Teaching Rationality Workshops

Neel NandaJan 3, 2021, 5:15 PM

42 points

9 comments30 min readEA link

Local Group Event Idea: EA Community Talks

Neel NandaDec 20, 2020, 5:12 PM

26 points

4 comments5 min readEA link

Make a Public Commitment to Writing EA Forum Posts

Neel NandaNov 18, 2020, 6:23 PM

21 points

11 comments1 min readEA link

Helping each other become more effective

Neel NandaOct 30, 2020, 9:33 PM

10 points

0 comments11 min readEA link

(www.neelnanda.io)