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. 78486
    Prev
    Next
    INDEX
    Explanations

    table with characteristics and values

    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
    _weight
    -0.08
    iosamente
    -0.08
     Lawrence
    -0.07
    Explain
    -0.07
    _has
    -0.07
    ful
    -0.07
    ohi
    -0.07
     uitleg
    -0.07
     higher
    -0.07
    Getty
    -0.07
    POSITIVE LOGITS
    値
    0.09
     answers
    0.08
     feminine
    0.08
     Angaben
    0.08
    .answers
    0.08
     menet
    0.08
     cau
    0.08
     щодо
    0.08
     nejlepší
    0.08
     Values
    0.08
    Activations Density 0.021%

    No Known Activations