© 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. 44295
    Prev
    Next
    INDEX
    Explanations

    Exercises

    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
    cesse
    -0.08
    內
    -0.08
    halts
    -0.08
     ಬದುಕ
    -0.08
     peligro
    -0.08
     pertes
    -0.07
    .SM
    -0.07
    スタ
    -0.07
    /-
    -0.07
    报道
    -0.07
    POSITIVE LOGITS
     orgasm
    0.08
     rehabil
    0.07
     ´
    0.07
     infert
    0.07
    _relu
    0.07
     ndarray
    0.07
    [q
    0.07
    _peak
    0.07
     lesbian
    0.07
    qubo
    0.07
    Activations Density 0.001%

    No Known Activations