© 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. 95620
    Prev
    Next
    INDEX
    Explanations

    cocktail recipes

    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
     kazan
    -0.08
     soja
    -0.08
    ブル
    -0.08
    十大
    -0.08
    .XML
    -0.08
     doesnt
    -0.07
     jurídicas
    -0.07
     centre
    -0.07
     tomatoes
    -0.07
    _xml
    -0.07
    POSITIVE LOGITS
     دستگاه
    0.08
     אמר
    0.08
     устройства
    0.08
    (rd
    0.08
    observer
    0.08
     Ideally
    0.07
     spectator
    0.07
     ప్రేక్షక
    0.07
     الجمهور
    0.07
     audience
    0.07
    Activations Density 0.010%

    No Known Activations