© 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. 11-RESID-POST-AA
    11. 47831
    Prev
    Next
    INDEX
    Explanations

    at

    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
     Polyester
    -0.08
     [-
    -0.08
    িলে
    -0.08
     Lut
    -0.08
     LR
    -0.08
     chipped
    -0.08
     ряда
    -0.08
     Laus
    -0.07
    orter
    -0.07
    eroon
    -0.07
    POSITIVE LOGITS
    人物
    0.09
    -themed
    0.09
    Vintage
    0.09
     futuristic
    0.08
    _TIMESTAMP
    0.08
     vintage
    0.08
    _timestamp
    0.08
     nostalgic
    0.08
    Timestamp
    0.08
     themed
    0.08
    Activations Density 0.003%

    No Known Activations