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. 112768
    Prev
    Next
    INDEX
    Explanations

    code

    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
     สุ
    -0.08
     categorías
    -0.08
     Categories
    -0.08
     strains
    -0.08
     Leider
    -0.08
    ’m
    -0.08
     üz
    -0.08
    _categories
    -0.08
     Nür
    -0.07
     andar
    -0.07
    POSITIVE LOGITS
     lexer
    0.11
     Lexer
    0.09
     parser
    0.09
    (Token
    0.09
    parser
    0.09
     LLVM
    0.09
     '('
    0.09
     "("
    0.09
     ::=
    0.09
     Atom
    0.09
    Activations Density 0.007%

    No Known Activations