© 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. 53
    Prev
    Next
    INDEX
    Explanations

    ociation

    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
    フト
    -0.08
     البر
    -0.08
    落实
    -0.08
    بر
    -0.08
     उत
    -0.07
    不足
    -0.07
     przec
    -0.07
    щина
    -0.07
     אויך
    -0.07
     linewidth
    -0.07
    POSITIVE LOGITS
     whining
    0.08
     Angry
    0.07
    nisse
    0.07
    žno
    0.07
     delas
    0.07
     Piazza
    0.07
     Cub
    0.07
     Iraq
    0.07
    mi
    0.07
     innovative
    0.07
    Activations Density 0.000%

    No Known Activations