© 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. 69575
    Prev
    Next
    INDEX
    Explanations

    skip

    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
     sépar
    -0.08
    sell
    -0.08
    ories
    -0.08
     competence
    -0.07
    WB
    -0.07
    sou
    -0.07
    ensity
    -0.07
    sf
    -0.07
    564
    -0.07
    メント
    -0.07
    POSITIVE LOGITS
    掉
    0.11
     verse
    0.09
     unnecessary
    0.09
     completely
    0.09
    pel
    0.08
     altogether
    0.08
    .Skip
    0.07
     விட்ட
    0.07
    �
    0.07
     unwanted
    0.07
    Activations Density 0.009%

    No Known Activations