© 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. 29726
    Prev
    Next
    INDEX
    Explanations

    sudden movement/change

    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
    _RS
    -0.08
    Wij
    -0.08
    (X
    -0.08
     Tweede
    -0.07
     تعليم
    -0.07
     towing
    -0.07
     Scenic
    -0.07
     Sikh
    -0.07
    /movie
    -0.07
     customization
    -0.07
    POSITIVE LOGITS
     intertw
    0.10
     intertwined
    0.10
     bobl
    0.08
     unfold
    0.08
    展开
    0.08
     hemen
    0.08
     unfolds
    0.08
     फैल
    0.08
    वत
    0.08
    空气
    0.08
    Activations Density 0.095%

    No Known Activations