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. 15-RESID-POST-AA
    6. 19404
    Prev
    Next
    INDEX
    Explanations

    Beauty and self-esteem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _sig
    -0.09
    .transaction
    -0.09
    Suspend
    -0.08
    Transaction
    -0.08
    (Transaction
    -0.08
    _watch
    -0.08
    事务
    -0.08
    _vm
    -0.08
     Suspend
    -0.08
     suspend
    -0.08
    POSITIVE LOGITS
     autoestima
    0.15
     피부
    0.14
    -esteem
    0.13
     aesthetic
    0.13
     skincare
    0.13
    美容
    0.13
     cosmetic
    0.13
     genital
    0.12
     البشرة
    0.12
     cellulite
    0.12
    Activations Density 0.064%

    No Known Activations