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. 15-RESID-POST-AA
    6. 19618
    Prev
    Next
    INDEX
    Explanations

    chat and responding to users

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .D
    -0.08
     D
    -0.08
    -
    -0.08
    -critical
    -0.07
     to
    -0.07
     that
    -0.07
    <|reserved_200016|>
    -0.07
     critical
    -0.07
     not
    -0.07
     atyp
    -0.07
    POSITIVE LOGITS
     presumably
    0.14
    ؟↵↵
    0.14
     ؟↵↵
    0.13
     ?↵↵
    0.13
     ???↵↵
    0.13
    ??↵↵
    0.13
    ?.↵↵
    0.13
     Probably
    0.12
    ?↵↵
    0.12
     vermutlich
    0.12
    Activations Density 0.206%

    No Known Activations