© 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. 7-RESID-POST-AA
    11. 1190
    Prev
    Next
    INDEX
    Explanations

    Christmas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dakar
    -0.09
     buck
    -0.08
    _expr
    -0.08
     bucks
    -0.08
     ble
    -0.08
     Shuttle
    -0.07
    _import
    -0.07
    _sensitive
    -0.07
     shuttle
    -0.07
    _frame
    -0.07
    POSITIVE LOGITS
     hosp
    0.09
     Weihnachts
    0.08
     fortnight
    0.08
    Division
    0.08
     Division
    0.08
     الطرف
    0.08
     cease
    0.08
     Engels
    0.08
     ডিসেম্বর
    0.08
     division
    0.08
    Activations Density 0.012%

    No Known Activations