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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65748
    Prev
    Next
    INDEX
    Explanations

    Auctions/Bidding

    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
     CIS
    -0.08
     MO
    -0.08
     CMD
    -0.08
    Geom
    -0.08
    Slice
    -0.08
    Kar
    -0.08
    MO
    -0.07
    (Component
    -0.07
     Gram
    -0.07
     massacre
    -0.07
    POSITIVE LOGITS
     budete
    0.09
     Throughout
    0.08
     Werbung
    0.08
     girlfriend
    0.08
    'hésitez
    0.08
    GING
    0.08
     thêm
    0.08
     jugu
    0.08
    助
    0.08
    助手
    0.08
    Activations Density 0.003%

    No Known Activations