© 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. 63324
    Prev
    Next
    INDEX
    Explanations

    mol

    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
     Spread
    -0.08
     ugly
    -0.08
     twisted
    -0.08
    uiting
    -0.08
    (mock
    -0.08
     Muk
    -0.08
    tschaft
    -0.08
    (as
    -0.08
    Judge
    -0.07
    ITY
    -0.07
    POSITIVE LOGITS
    ^{-
    0.11
    −
    0.09
    ¬
    0.08
     которого
    0.08
    ='<?
    0.08
     creep
    0.08
     <!
    0.08
    -wise
    0.08
    =<?
    0.08
    ^-
    0.08
    Activations Density 0.006%

    No Known Activations