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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 88052
    Prev
    Next
    INDEX
    Explanations

    breast

    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
     seguros
    -0.09
     excelencia
    -0.08
    োনা
    -0.08
    typeparam
    -0.08
    titor
    -0.08
    יבי
    -0.08
    .Throw
    -0.08
     ụtọ
    -0.08
     peligros
    -0.08
     temporada
    -0.08
    POSITIVE LOGITS
     ridge
    0.08
     sudo
    0.08
     gib
    0.08
     brit
    0.08
     penile
    0.07
     barren
    0.07
     penis
    0.07
     القض
    0.07
     bloss
    0.07
     Ridge
    0.07
    Activations Density 0.003%

    No Known Activations