© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 611
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
     ਹਾਂ
    -0.08
     viva
    -0.08
     totes
    -0.07
     regime
    -0.07
     heerlijke
    -0.07
    urf
    -0.07
     Trop
    -0.07
     probablement
    -0.07
     coalition
    -0.07
    、と
    -0.07
    POSITIVE LOGITS
    当前位置
    0.08
     Stewart
    0.08
     resetting
    0.07
    ડા
    0.07
     dicha
    0.07
     среды
    0.07
     seguida
    0.07
     splitting
    0.07
     hens
    0.07
     posición
    0.07
    Activations Density 0.084%

    No Known Activations