© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68102
    Prev
    Next
    INDEX
    Explanations

    """

    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
    LER
    -0.08
     audience
    -0.08
     हाथ
    -0.08
     gehe
    -0.08
     kuita
    -0.08
     teeb
    -0.08
     phân
    -0.08
    轨
    -0.07
    .Gui
    -0.07
    alc
    -0.07
    POSITIVE LOGITS
    bib
    0.09
     YYYY
    0.08
    _UTF
    0.08
    ASCII
    0.08
    emoji
    0.08
    |||
    0.08
    viral
    0.08
     emojis
    0.08
    Emoji
    0.08
     commas
    0.08
    Activations Density 0.000%

    No Known Activations