© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70985
    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
    تان
    -0.09
    قرر
    -0.08
     sexes
    -0.08
     intermedi
    -0.08
     sø
    -0.08
     Sense
    -0.07
     intermediate
    -0.07
    少年
    -0.07
    قر
    -0.07
     ä
    -0.07
    POSITIVE LOGITS
    Worst
    0.08
    最
    0.08
     harsh
    0.08
     Worst
    0.08
    SPI
    0.08
    �
    0.08
     vigilant
    0.08
    责
    0.07
    xim
    0.07
    粗
    0.07
    Activations Density 0.012%

    No Known Activations