© 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. 735
    Prev
    Next
    INDEX
    Explanations

    →

    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
     eingerichtet
    -0.08
     Einrichtung
    -0.07
     MI
    -0.07
    (ar
    -0.07
     com
    -0.07
    _tok
    -0.07
     ঠিক
    -0.07
     configurar
    -0.07
     thresholds
    -0.07
     therm
    -0.07
    POSITIVE LOGITS
    535
    0.08
     hurry
    0.08
    river
    0.08
    anthem
    0.08
    425
    0.08
    Rpt
    0.08
     안
    0.07
     shaker
    0.07
     expansión
    0.07
    687
    0.07
    Activations Density 0.000%

    No Known Activations