© 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. 69511
    Prev
    Next
    INDEX
    Explanations

    3

    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
    ísimo
    -0.07
     आल
    -0.07
    olem
    -0.07
    Payload
    -0.07
     toetsen
    -0.07
     có
    -0.07
     cùng
    -0.07
    .Sound
    -0.07
     luật
    -0.07
    versation
    -0.07
    POSITIVE LOGITS
    கவ
    0.08
     retinal
    0.07
    /her
    0.07
    ,obj
    0.07
    等等
    0.07
    DBC
    0.07
     frankly
    0.07
     Women
    0.07
    важа
    0.07
     downright
    0.06
    Activations Density 0.003%

    No Known Activations