© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94731
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
    awi
    -0.09
     Lod
    -0.08
     locais
    -0.08
     называют
    -0.08
    -language
    -0.08
    чив
    -0.07
     YO
    -0.07
     bateau
    -0.07
     Lucy
    -0.07
    óp
    -0.07
    POSITIVE LOGITS
     വരെ
    0.09
     পর্যন্ত
    0.09
     limitée
    0.09
     maximum
    0.08
    .annotation
    0.08
     వరకు
    0.08
    limited
    0.08
     capabilities
    0.08
    まで
    0.08
     limitada
    0.08
    Activations Density 0.075%

    No Known Activations