© 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. 112628
    Prev
    Next
    INDEX
    Explanations

    ACT

    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
     někol
    -0.09
     elems
    -0.09
    Elems
    -0.08
     [+
    -0.08
     коронавирус
    -0.07
    Coronavirus
    -0.07
     Ops
    -0.07
     dens
    -0.07
     Coronavirus
    -0.07
     Exclusive
    -0.07
    POSITIVE LOGITS
     euth
    0.08
    林
    0.08
    zell
    0.07
    方法
    0.07
    专业
    0.07
    令
    0.07
     habitual
    0.07
     spiders
    0.07
    �
    0.07
    .cx
    0.07
    Activations Density 0.001%

    No Known Activations