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. 30733
    Prev
    Next
    INDEX
    Explanations

    radius

    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
     kinet
    -0.09
    나요
    -0.08
    \d
    -0.08
    جب
    -0.07
    What's
    -0.07
     drought
    -0.07
     understandably
    -0.07
     météo
    -0.07
     basé
    -0.07
    Whatever
    -0.07
    POSITIVE LOGITS
    左右
    0.09
    ,因为
    0.08
     aron
    0.08
     Makes
    0.07
    ,因此
    0.07
    onha
    0.07
     لت
    0.07
    ikos
    0.07
    ,使
    0.07
     آم
    0.07
    Activations Density 0.019%

    No Known Activations