© 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. 111177
    Prev
    Next
    INDEX
    Explanations

    delay

    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
     рӯзи
    -0.10
     délais
    -0.09
     χρον
    -0.09
    зода
    -0.09
     studying
    -0.09
     Groupon
    -0.09
     Тай
    -0.09
    рӯз
    -0.09
     մայր
    -0.09
    erio
    -0.09
    POSITIVE LOGITS
     created
    0.07
     brand
    0.07
    _person
    0.07
    akana
    0.07
     mus
    0.07
    iser
    0.07
     management
    0.07
    Management
    0.07
     prints
    0.07
    .db
    0.07
    Activations Density 0.000%

    No Known Activations