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. 23632
    Prev
    Next
    INDEX
    Explanations

    copy

    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
     affection
    -0.08
     farmland
    -0.08
     ಇಂದು
    -0.07
     ಸಂಖ್ಯೆ
    -0.07
    Kent
    -0.07
    imerk
    -0.07
     intimid
    -0.07
     prominently
    -0.07
     inland
    -0.07
     intim
    -0.07
    POSITIVE LOGITS
     그대로
    0.12
     intact
    0.10
     unchanged
    0.09
    无需
    0.09
    -existing
    0.09
     zaten
    0.08
    .deepcopy
    0.08
    _existing
    0.08
    /raw
    0.08
     direkten
    0.08
    Activations Density 0.008%

    No Known Activations