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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 130989
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
    干部
    -0.08
    昵称
    -0.08
     séance
    -0.08
     Clothes
    -0.07
     degrade
    -0.07
     nick
    -0.07
    eldig
    -0.07
    ыя
    -0.07
     contraseña
    -0.07
    POSITIVE LOGITS
     headquartered
    0.09
    同行
    0.08
     ASEAN
    0.08
     səh
    0.08
     progressive
    0.08
     바
    0.08
    香港
    0.07
    事項
    0.07
     CGI
    0.07
    ーダ
    0.07
    Activations Density 0.038%

    No Known Activations