© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91423
    Prev
    Next
    INDEX
    Explanations

    Prototypical Networks

    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
     Zurich
    -0.08
    azed
    -0.08
     richest
    -0.08
     aston
    -0.08
    Ole
    -0.07
    _iters
    -0.07
    azu
    -0.07
     Billion
    -0.07
     qof
    -0.07
     taj
    -0.07
    POSITIVE LOGITS
     grandparents
    0.09
     व्यवस्थ
    0.09
     référence
    0.08
     engraved
    0.08
     estratégias
    0.08
    drá
    0.08
     Crud
    0.08
     हात
    0.08
     reference
    0.08
     haverá
    0.08
    Activations Density 0.001%

    No Known Activations