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. 60880
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    Var
    -0.08
    Clay
    -0.07
    ,string
    -0.07
    -0.07
    vars
    -0.07
    Pier
    -0.07
    Cl
    -0.07
    string
    -0.07
     ble
    -0.07
     eel
    -0.07
    POSITIVE LOGITS
     Horizontal
    0.09
    ෙන්
    0.08
     موت
    0.08
     ดู
    0.08
     schauen
    0.08
    นคร
    0.08
    âns
    0.08
     байни
    0.08
     भोज
    0.08
    ジャン
    0.08
    Activations Density 0.009%

    No Known Activations