Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112182
    Prev
    Next
    INDEX
    Explanations

    of

    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
     соответствии
    -0.08
    本人
    -0.08
     Stat
    -0.08
     Gesam
    -0.07
    _problem
    -0.07
     официаль
    -0.07
    stelling
    -0.07
    stellen
    -0.07
    ificate
    -0.07
     CRS
    -0.07
    POSITIVE LOGITS
    ंटी
    0.09
     superfície
    0.09
    र्मी
    0.08
     vindo
    0.08
    厨房
    0.08
     formando
    0.08
    $list
    0.08
    cier
    0.08
     olha
    0.08
    鸭
    0.08
    Activations Density 0.009%

    No Known Activations