© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111217
    Prev
    Next
    INDEX
    Explanations

    The card game "Set"

    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
     organisé
    -0.08
     bankroll
    -0.08
    財
    -0.08
     signage
    -0.08
    企業
    -0.08
     kuruluş
    -0.08
     contractor
    -0.08
     financière
    -0.07
     polling
    -0.07
     корпоратив
    -0.07
    POSITIVE LOGITS
    _predict
    0.08
     Eugen
    0.08
     ml
    0.08
     belief
    0.08
    ihin
    0.08
     creemos
    0.08
    confidence
    0.08
     whining
    0.07
    Gradu
    0.07
    mlu
    0.07
    Activations Density 0.002%

    No Known Activations