© 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. 5889
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     Uncategorized
    -0.08
    ooda
    -0.08
    STRING
    -0.08
    ిస్
    -0.08
    ಿಸ್
    -0.08
    виж
    -0.08
    CC
    -0.08
    ിസ്
    -0.07
    VARCHAR
    -0.07
     cousin
    -0.07
    POSITIVE LOGITS
     invert
    0.09
     inode
    0.08
    invert
    0.08
     بىلەن
    0.08
    ह
    0.08
    утат
    0.08
    نى
    0.08
    менты
    0.08
    Invert
    0.08
    ندی
    0.08
    Activations Density 0.002%

    No Known Activations