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. 30671
    Prev
    Next
    INDEX
    Explanations

    life

    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
     leves
    -0.09
     delito
    -0.07
     sekt
    -0.07
    .coin
    -0.07
     Maur
    -0.07
     strength
    -0.07
     sadd
    -0.07
     ocas
    -0.07
    물
    -0.07
     Hoch
    -0.07
    POSITIVE LOGITS
     동안
    0.10
    -lasting
    0.10
    동안
    0.09
    是多少
    0.09
    dauer
    0.09
    裕
    0.09
    -lived
    0.08
    有限
    0.08
    chrome
    0.08
    owatt
    0.08
    Activations Density 0.017%

    No Known Activations