OpenAI Researcher Claims Most Large Model Neurons Are Interpretable
Former OpenAI researcher Nick Cammarata claims that with modern agentic tools, the vast majority of neurons in trillion-parameter models are now legible, overturning earlier pessimism about neural networks being arbitrary tangled knots. He suggests mechanistic interpretability may be solved soon as automated scientists improve, citing a 'bitter lesson' where simple methods work at absurd scale. Sam Altman endorsed this view.
Full Report
Sam Altman (@sama) · 2026-10-16 16
Very happy to see this from Nick!
↳ 引用 @nickcammarata (Nick): interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works