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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 44990
    Prev
    Next
    INDEX
    Explanations

    Programming and command-line tools

    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
    .GONE
    -0.08
     ọch
    -0.08
     kanal
    -0.08
    kụ
    -0.08
     Sight
    -0.08
     кок
    -0.08
     dž
    -0.07
     buggy
    -0.07
     Indoor
    -0.07
    tagon
    -0.07
    POSITIVE LOGITS
     liqu
    0.08
    -like
    0.08
     language
    0.08
     الفي
    0.08
     extern
    0.08
     physic
    0.07
    -inspired
    0.07
    -language
    0.07
     زبان
    0.07
     physics
    0.07
    Activations Density 0.053%

    No Known Activations