© 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. 111147
    Prev
    Next
    INDEX
    Explanations

    activity diagrams

    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
     reds
    -0.08
    Smoke
    -0.08
     smoke
    -0.07
     kaliteli
    -0.07
    设置
    -0.07
     Smoke
    -0.07
    当天
    -0.07
    偷拍
    -0.07
    .click
    -0.07
    itchie
    -0.07
    POSITIVE LOGITS
     Sturm
    0.09
     Spare
    0.08
     संविधान
    0.08
     граждан
    0.08
     ruling
    0.08
     successors
    0.08
    Flex
    0.08
     Flex
    0.07
    azole
    0.07
     boolean
    0.07
    Activations Density 0.001%

    No Known Activations