Critique adds: "Already Clean" essay also mischaracterizes curve detectors and SAE prior work

livgorton · x · 2026-10-21

Adding a fourth concern, Liv Gorton says that beyond the superposition definition issues, Cammarata's essay confuses or mischaracterizes other prior work, including her research on curve detectors and SAEs.

Related event: Anthropic researcher rebuts "Neural Networks Are Already Clean" claim point by point(7 posts)→

Original post →

More from Research

Research channel →