Goodfire chief scientist Tom McGrath on interpretability: SAEs may fracture what networks really learn

Machine Learning Street Talk · youtube · 2026-09-03

Machine Learning Street Talk hosts Tom McGrath, co-founder and Chief Scientist at Goodfire and ex-DeepMind researcher, for a deep dive into what neural networks actually learn.

Key threads:

The episode comes with an extensive paper list (Emergent Misalignment, Persona Vectors, Features as Rewards, and more) and full timestamps.

Original post →

More from Research

Research channel →