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. 60661
    Prev
    Next
    INDEX
    Explanations

    algebraic substitution variables

    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
    elite
    -0.08
    แบ
    -0.07
     Rolex
    -0.07
    Ultra
    -0.07
     Exodus
    -0.07
     Gef
    -0.07
    veilig
    -0.07
    Crystal
    -0.07
     dess
    -0.07
     Funktion
    -0.07
    POSITIVE LOGITS
    apọ
    0.09
    ,sum
    0.09
     tổng
    0.08
     agreed
    0.08
     zbir
    0.08
     Trung
    0.08
    -components
    0.07
     singles
    0.07
    ,width
    0.07
    ,tr
    0.07
    Activations Density 0.026%

    No Known Activations