© 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. 65528
    Prev
    Next
    INDEX
    Explanations

    Direct or Real

    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
    -used
    -0.08
    ’ing
    -0.08
    .AG
    -0.08
    leck
    -0.08
    alsex
    -0.08
     Lade
    -0.08
    -array
    -0.08
     והת
    -0.08
     ופ
    -0.08
     alls
    -0.07
    POSITIVE LOGITS
     
    0.09
    Quote
    0.08
    ുന്നതിന
    0.08
     résumé
    0.08
     jurídicas
    0.07
     cálculo
    0.07
     quoting
    0.07
    Job
    0.07
     Quotes
    0.07
     conhe
    0.07
    Activations Density 0.715%

    No Known Activations