© 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 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. 69603
    Prev
    Next
    INDEX
    Explanations

    pull

    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
     statist
    -0.07
    ologists
    -0.07
     Journalism
    -0.07
    istical
    -0.07
     lleno
    -0.07
     journalists
    -0.07
     performances
    -0.07
    .broadcast
    -0.07
    enal
    -0.07
    充
    -0.07
    POSITIVE LOGITS
     pux
    0.10
    .Pull
    0.09
     删除
    0.09
     ખે
    0.09
    删除
    0.09
     deleting
    0.08
     拉
    0.08
     rope
    0.08
     pulling
    0.08
     Rope
    0.08
    Activations Density 0.013%

    No Known Activations