© 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. 54754
    Prev
    Next
    INDEX
    Explanations

    Overtraining and exercise

    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
    dew
    -0.08
    aisin
    -0.08
    Corners
    -0.07
    িঠ
    -0.07
    aiser
    -0.07
    actors
    -0.07
    莫
    -0.07
     asylum
    -0.07
     snee
    -0.07
     الوا
    -0.07
    POSITIVE LOGITS
     competing
    0.10
     burnout
    0.10
     प्रशिक्षण
    0.10
     workouts
    0.10
     competitions
    0.09
     sauna
    0.09
     трениров
    0.09
     trän
    0.09
     gimnasio
    0.09
     جاتی
    0.09
    Activations Density 0.009%

    No Known Activations