© 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. 47999
    Prev
    Next
    INDEX
    Explanations

    glass

    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
     Conan
    -0.08
    156
    -0.08
     Urbana
    -0.08
    507
    -0.08
     "-
    -0.07
     પોલીસ
    -0.07
    laug
    -0.07
     LAW
    -0.07
     Connor
    -0.07
     Π
    -0.07
    POSITIVE LOGITS
     вся
    0.09
     соедин
    0.09
     үйл
    0.09
     аксесс
    0.08
    চিত
    0.08
     себ
    0.08
     распростран
    0.08
     кок
    0.08
     проник
    0.08
     सारी
    0.08
    Activations Density 0.007%

    No Known Activations