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. 75889
    Prev
    Next
    INDEX
    Explanations

    Influencing someone's actions

    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
    列表
    -0.08
    海道
    -0.08
     bytes
    -0.07
    大量
    -0.07
    lists
    -0.07
    _bytes
    -0.07
     fun
    -0.07
    mek
    -0.07
     ample
    -0.07
    列
    -0.07
    POSITIVE LOGITS
     overwhelmed
    0.09
     hatred
    0.09
     preju
    0.09
     derail
    0.08
     disruptions
    0.08
     영향을
    0.08
     undue
    0.08
    Portugal
    0.08
    ,坚持
    0.08
     inconven
    0.08
    Activations Density 0.043%

    No Known Activations