© 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. 3-RESID-POST-AA
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    neural network models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umu
    -0.08
     sn
    -0.08
     filmed
    -0.08
     releg
    -0.07
    Smile
    -0.07
    /sn
    -0.07
    ?")↵
    -0.07
     Yok
    -0.07
     عبارت
    -0.07
    trainer
    -0.07
    POSITIVE LOGITS
     rockets
    0.09
     армии
    0.08
     mmadụ
    0.08
    سرائيلية
    0.08
     helicopters
    0.08
     mutane
    0.08
     ụgbọ
    0.07
     kone
    0.07
    -high
    0.07
     Fortress
    0.07
    Activations Density 0.005%

    No Known Activations