Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30867
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    aha
    -0.08
    QR
    -0.07
     المد
    -0.07
     mg
    -0.07
     soaps
    -0.07
     piccoli
    -0.07
    raq
    -0.07
     maliit
    -0.07
     shards
    -0.07
    :r
    -0.07
    POSITIVE LOGITS
     résumé
    0.09
    gie
    0.08
     König
    0.08
     verstehen
    0.08
    ാപ്പ
    0.08
     prob
    0.08
    Warum
    0.07
     erfahren
    0.07
     важно
    0.07
     efficacement
    0.07
    Activations Density 0.086%

    No Known Activations