© 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. 31093
    Prev
    Next
    INDEX
    Explanations

    [contains

    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
     nylon
    -0.08
    _extend
    -0.07
     azy
    -0.07
    woven
    -0.07
     OB
    -0.07
    CDF
    -0.07
     Extended
    -0.07
     organismo
    -0.07
     Guidelines
    -0.07
    cdf
    -0.07
    POSITIVE LOGITS
    ақты
    0.08
     degree
    0.08
    gratis
    0.07
    anfaat
    0.07
     подходит
    0.07
    ичный
    0.07
    илли
    0.07
     подойдет
    0.07
    annon
    0.07
     Peel
    0.07
    Activations Density 0.001%

    No Known Activations