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. 77390
    Prev
    Next
    INDEX
    Explanations

    typed

    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
    范围
    -0.08
    _range
    -0.08
    _logout
    -0.08
    ylon
    -0.08
     RANGE
    -0.08
    .movie
    -0.08
    ün
    -0.07
    敌
    -0.07
     wol
    -0.07
    .logout
    -0.07
    POSITIVE LOGITS
    ুশ
    0.09
     outsourced
    0.09
     matur
    0.08
     supervise
    0.08
     дас
    0.08
    Revision
    0.08
    خصصة
    0.08
     проблем
    0.08
     Betreuung
    0.08
     postage
    0.08
    Activations Density 0.004%

    No Known Activations