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. 19478
    Prev
    Next
    INDEX
    Explanations

    say period

    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
    ",
    -0.08
    )、
    -0.08
    ),
    -0.08
    Resolve
    -0.07
     Physi
    -0.07
     haben
    -0.07
     rood
    -0.07
     Baron
    -0.07
    ='';↵
    -0.07
     duwe
    -0.07
    POSITIVE LOGITS
    。↵↵
    0.17
    ۔↵↵
    0.17
    !↵↵
    0.14
    ។↵↵
    0.14
    。”↵↵
    0.14
    .↵↵
    0.13
    ।↵↵
    0.13
    ။↵↵
    0.13
    ♡↵↵
    0.13
    。」↵↵
    0.13
    Activations Density 0.077%

    No Known Activations