© 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. 29616
    Prev
    Next
    INDEX
    Explanations

    Chinese characteristics

    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
    (colors
    -0.08
     and
    -0.08
    UK
    -0.07
     Canada
    -0.07
    (days
    -0.07
     UK
    -0.07
    JJ
    -0.07
     debilitating
    -0.07
    ,
    -0.07
    END
    -0.07
    POSITIVE LOGITS
    ოტ
    0.09
     Webinar
    0.08
     रास्त
    0.08
    ატივ
    0.08
    როპ
    0.08
     Strait
    0.08
     ტურ
    0.08
     webinar
    0.08
     surrogate
    0.08
    როს
    0.08
    Activations Density 0.001%

    No Known Activations