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. 58719
    Prev
    Next
    INDEX
    Explanations

    implement

    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
    陷
    -0.08
     Ek
    -0.07
     为
    -0.07
     investigator
    -0.07
    投
    -0.07
    為
    -0.07
    (cl
    -0.07
     empregado
    -0.07
     investigation
    -0.06
     backlog
    -0.06
    POSITIVE LOGITS
     bachelors
    0.09
     ګڼ
    0.08
     הול
    0.08
    ګي
    0.08
     separados
    0.08
     تھے
    0.08
     terminó
    0.08
    elah
    0.07
    ادی
    0.07
    Went
    0.07
    Activations Density 0.002%

    No Known Activations