© 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. 79122
    Prev
    Next
    INDEX
    Explanations

    Otto von Bismarck

    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
    (valid
    -0.09
     safety
    -0.08
    ождении
    -0.08
    -share
    -0.08
    応募
    -0.08
     προβ
    -0.08
     concurrent
    -0.08
     inhal
    -0.07
    .svg
    -0.07
     inhale
    -0.07
    POSITIVE LOGITS
     indispens
    0.09
     Fiscal
    0.08
     cunning
    0.08
    smart
    0.08
    导
    0.08
     SMART
    0.07
     tona
    0.07
     MST
    0.07
     fiscal
    0.07
    temporary
    0.07
    Activations Density 0.003%

    No Known Activations