© 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. 44463
    Prev
    Next
    INDEX
    Explanations

    idioms

    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
    昆
    -0.08
     받을
    -0.08
     almak
    -0.08
    午
    -0.08
    -0.08
     Selbst
    -0.08
    sorting
    -0.08
     六合
    -0.08
    sorted
    -0.07
    自主
    -0.07
    POSITIVE LOGITS
     idi
    0.11
    俗
    0.09
    .Exceptions
    0.09
     sayings
    0.08
     collo
    0.08
     slang
    0.08
     Idi
    0.08
     contractions
    0.08
    Idi
    0.08
     lifestyle
    0.08
    Activations Density 0.011%
    No Known Activations