© 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 EvalsExportsinterp-engineNEWAPI 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. 111383
    Prev
    Next
    INDEX
    Explanations

    anatomy

    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
    ોશ
    -0.07
    -fer
    -0.07
     deelt
    -0.07
    .fr
    -0.07
     Haiti
    -0.07
    Cape
    -0.07
     Cayman
    -0.07
     Picasso
    -0.07
     sichtbar
    -0.07
    .imgur
    -0.07
    POSITIVE LOGITS
    יצור
    0.08
    ERCIAL
    0.08
     requis
    0.08
    жения
    0.08
     оригин
    0.08
     tạo
    0.07
     guten
    0.07
     presión
    0.07
    _GET
    0.07
    екция
    0.07
    Activations Density 0.000%

    No Known Activations