© 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. 45350
    Prev
    Next
    INDEX
    Explanations

    intersect

    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
     variante
    -0.07
    ODS
    -0.07
     remember
    -0.07
     وص
    -0.07
    SPORT
    -0.07
    _csv
    -0.07
     vollständig
    -0.07
     Linked
    -0.07
    Quelle
    -0.07
     gekopp
    -0.07
    POSITIVE LOGITS
     lenn
    0.08
     interiores
    0.08
     Dart
    0.08
    unye
    0.08
     medial
    0.08
    ित
    0.07
     Tender
    0.07
     служ
    0.07
     freeway
    0.07
     midpoint
    0.07
    Activations Density 0.017%

    No Known Activations