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. 53013
    Prev
    Next
    INDEX
    Explanations

    VAR

    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
    .transform
    -0.09
    '[
    -0.08
    ās
    -0.08
    тыры
    -0.08
    vari
    -0.08
    wee
    -0.08
    wn
    -0.07
     trasform
    -0.07
     vari
    -0.07
    essaan
    -0.07
    POSITIVE LOGITS
    판
    0.08
     lief
    0.07
     제외
    0.07
     Vila
    0.07
     실패
    0.07
    excluded
    0.07
     любое
    0.07
    _ram
    0.07
     trygg
    0.07
     Paradise
    0.07
    Activations Density 0.000%

    No Known Activations