© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96719
    Prev
    Next
    INDEX
    Explanations

    Formatted documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maybe
    -0.15
     maybe
    -0.14
     有没有
    -0.12
     vielleicht
    -0.12
     शायद
    -0.12
    有没有
    -0.12
     그런데
    -0.12
     malah
    -0.12
     THEN
    -0.11
     뭐
    -0.11
    POSITIVE LOGITS
     Please
    0.23
    Please
    0.22
     Note
    0.21
    Note
    0.20
     please
    0.18
    _note
    0.18
     veuillez
    0.18
    >Please
    0.17
    Veuillez
    0.17
    _All
    0.17
    Activations Density 0.176%

    No Known Activations