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. 30420
    Prev
    Next
    INDEX
    Explanations

    character encoding/coding

    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
     soreness
    -0.10
     neglected
    -0.09
     crimin
    -0.09
    cas
    -0.09
     journal
    -0.08
     jeans
    -0.08
     sustainability
    -0.08
    rut
    -0.08
     grime
    -0.08
    wirkung
    -0.08
    POSITIVE LOGITS
     Huff
    0.09
    _encoded
    0.09
    encoded
    0.08
    Encoded
    0.08
     Unary
    0.08
    编码
    0.08
    _encode
    0.08
     +=
    0.08
     streamer
    0.08
    (TYPE
    0.08
    Activations Density 0.004%

    No Known Activations