© 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. 25063
    Prev
    Next
    INDEX
    Explanations

    barely

    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
     Andal
    -0.09
    dram
    -0.07
    Se
    -0.07
     æ
    -0.07
    apons
    -0.07
    useppe
    -0.07
    Obrigado
    -0.07
    inel
    -0.07
    инок
    -0.07
    uyo
    -0.07
    POSITIVE LOGITS
     barely
    0.10
     nổi
    0.08
     نست
    0.08
    同期
    0.08
    (stream
    0.08
    -अ
    0.08
     inger
    0.08
    वाही
    0.07
     scraped
    0.07
     bud
    0.07
    Activations Density 0.008%

    No Known Activations