© 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. 95348
    Prev
    Next
    INDEX
    Explanations

    visible

    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
     cop
    -0.08
    hero
    -0.08
    ದ
    -0.07
     இச
    -0.07
    -0.07
     फिर
    -0.07
     ಗ
    -0.07
     응
    -0.07
     Pun
    -0.07
     жест
    -0.07
    POSITIVE LOGITS
    -cut
    0.09
    的时候
    0.08
     Ban
    0.08
     Viva
    0.08
     جداً
    0.08
     svo
    0.08
     claramente
    0.08
    丽
    0.08
    闪
    0.08
     banget
    0.08
    Activations Density 0.012%
    No Known Activations