© 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. 112367
    Prev
    Next
    INDEX
    Explanations

    =

    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
     Brandenburg
    -0.07
    uder
    -0.07
    িং
    -0.07
     toler
    -0.07
    Breed
    -0.07
     tham
    -0.07
     specifications
    -0.07
     تصل
    -0.07
    >[↵
    -0.07
     Tail
    -0.07
    POSITIVE LOGITS
     нез
    0.09
     хоч
    0.08
    ことで
    0.08
     proves
    0.08
     restruct
    0.08
    larından
    0.07
    绑定
    0.07
    解绑
    0.07
     축
    0.07
    Ай
    0.07
    Activations Density 0.027%

    No Known Activations