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. 102846
    Prev
    Next
    INDEX
    Explanations

    genetics

    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
     isset
    -0.08
    .kw
    -0.08
    orderby
    -0.08
    和值
    -0.08
    /widget
    -0.08
     tostring
    -0.08
    (queue
    -0.08
    .hash
    -0.08
    ored
    -0.08
     nonprofit
    -0.08
    POSITIVE LOGITS
     males
    0.10
     east
    0.09
     geographically
    0.09
     south
    0.09
     Euras
    0.08
     southeast
    0.08
     populations
    0.08
     archaeological
    0.08
     Bl
    0.08
     west
    0.08
    Activations Density 0.012%

    No Known Activations