© 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. 129157
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE

    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
     Shay
    -0.07
     grandfather
    -0.07
     exceptions
    -0.07
     quarry
    -0.07
     sectional
    -0.07
    quet
    -0.07
     conj
    -0.07
    ytte
    -0.07
    Vel
    -0.07
    Exceptions
    -0.07
    POSITIVE LOGITS
     erbjuder
    0.08
     Dys
    0.08
    ;base
    0.08
     koń
    0.08
     زیر
    0.07
    <head
    0.07
    <html
    0.07
     스
    0.07
     предлагает
    0.07
     Interim
    0.07
    Activations Density 0.001%

    No Known Activations