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. 54266
    Prev
    Next
    INDEX
    Explanations

    pandas (python library)

    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
     punishment
    -0.10
    CHAT
    -0.09
     punish
    -0.09
     selfish
    -0.09
     criminal
    -0.08
    /chat
    -0.08
    奖
    -0.08
     coward
    -0.08
     sham
    -0.08
    Penalty
    -0.08
    POSITIVE LOGITS
    .astype
    0.11
    .xlsx
    0.11
    .load
    0.11
    .Excel
    0.10
    .iloc
    0.10
    .read
    0.10
    .imread
    0.09
    .csv
    0.09
    _csv
    0.09
    _excel
    0.09
    Activations Density 0.009%

    No Known Activations