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. 78339
    Prev
    Next
    INDEX
    Explanations

    Fold

    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
     zen
    -0.08
    pair
    -0.08
    _sid
    -0.08
    _PAIR
    -0.08
    zugehen
    -0.07
    643
    -0.07
    HDR
    -0.07
    duplic
    -0.07
     node
    -0.07
    pin
    -0.07
    POSITIVE LOGITS
    印度
    0.08
     hurdles
    0.08
     DON
    0.08
     đấu
    0.08
    打造
    0.07
     ವಿಷಯ
    0.07
     respectable
    0.07
     menarik
    0.07
    pekte
    0.07
     HBO
    0.07
    Activations Density 0.003%

    No Known Activations