Experiments probe whether a "Claude neuron" really exists

Sauers showed that a style vector derived from "Claude minus other models" can make outputs read like Claude, but neither Opus 5.5 nor Astra could identify a genuine "Claude neuron," leaving its existence unconfirmed.

2026-10-19 ~ 2026-10-19 · 3 related posts

• Steering a single trained neuron makes models claim they're Claude, experiment shows — Sauers_ · 2026-10-19
• Fun experiment: Opus 5.5 and Astra both fail to spot the Claude neuron — Sauers_ · 2026-10-19
• Testing "Claude neurons" in Qwen3-8B: no better than random neurons — Sauers_ · 2026-10-19