© 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. 113445
    Prev
    Next
    INDEX
    Explanations

    Olympics and winning

    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
     Warp
    -0.08
     irregular
    -0.08
    UGH
    -0.07
     Barrel
    -0.07
    .Next
    -0.07
     Vaugh
    -0.07
    -X
    -0.07
     Latest
    -0.07
    -TV
    -0.07
    .Size
    -0.07
    POSITIVE LOGITS
     gagal
    0.09
    ��
    0.08
     Sarajevo
    0.08
     inauguration
    0.08
     fetal
    0.08
     Staffel
    0.08
     fetus
    0.08
    不过
    0.07
     نتائج
    0.07
    wasser
    0.07
    Activations Density 0.011%

    No Known Activations