© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29568
    Prev
    Next
    INDEX
    Explanations

    compiling source 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
     denominations
    -0.09
     vividly
    -0.08
     Cartier
    -0.08
    tooltip
    -0.08
    Tooltip
    -0.08
     Pois
    -0.08
    红包
    -0.08
     شبکه
    -0.08
     gwa
    -0.08
    ;color
    -0.07
    POSITIVE LOGITS
     compile
    0.11
     Compile
    0.10
    Compile
    0.10
    Compilation
    0.10
    .cpp
    0.09
     comprising
    0.09
     comprises
    0.09
    _compile
    0.09
    clang
    0.09
     assembler
    0.09
    Activations Density 0.008%

    No Known Activations