© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54755
    Prev
    Next
    INDEX
    Explanations

    nested math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Sub
    -0.08
    Teach
    -0.07
     surprisingly
    -0.07
     Münster
    -0.07
    .Our
    -0.07
    endor
    -0.07
     दूर
    -0.07
    ,min
    -0.07
    }↵↵↵↵↵↵
    -0.07
     cous
    -0.07
    POSITIVE LOGITS
     gebouw
    0.10
     arrêt
    0.09
     arrêté
    0.08
     Gerät
    0.08
    /show
    0.08
    bagai
    0.08
    jsp
    0.08
     blade
    0.08
    /errors
    0.07
    ями
    0.07
    Activations Density 0.002%

    No Known Activations