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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94450
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
     franch
    -0.08
     FR
    -0.08
     PAG
    -0.08
     cancellation
    -0.07
     FIG
    -0.07
     faker
    -0.07
     Francis
    -0.07
     Franchise
    -0.07
    strument
    -0.07
     laman
    -0.07
    POSITIVE LOGITS
     impresionante
    0.07
    .ad
    0.07
     عکس
    0.07
     Bud
    0.07
     برا
    0.07
    Holding
    0.07
    /weather
    0.07
    ‌ای
    0.07
     ف
    0.07
    함
    0.07
    Activations Density 0.006%

    No Known Activations