© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95749
    Prev
    Next
    INDEX
    Explanations

    Russian language

    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
    .pl
    -0.08
    utation
    -0.07
    .api
    -0.07
    'post
    -0.07
     combine
    -0.07
    .program
    -0.07
    'application
    -0.07
    _faces
    -0.07
    用于
    -0.07
    ">↵↵↵
    -0.07
    POSITIVE LOGITS
     inadvert
    0.13
     unintended
    0.12
     inadvertently
    0.11
     horas
    0.10
    unexpected
    0.10
     engross
    0.10
     Hours
    0.10
     बित
    0.09
     hours
    0.09
     മണിക്ക
    0.09
    Activations Density 0.058%

    No Known Activations