© 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. 23-RESID-POST-AA
    11. 50466
    Prev
    Next
    INDEX
    Explanations

    предпоч

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stich
    -0.09
    ji
    -0.08
    .activate
    -0.07
    ши
    -0.07
     SPE
    -0.07
    ші
    -0.07
    ський
    -0.07
     Sullivan
    -0.07
    ଚ
    -0.07
     번째
    -0.07
    POSITIVE LOGITS
    ита
    0.14
    итайте
    0.13
    ит
    0.12
    итать
    0.12
    тет
    0.11
    iebt
    0.10
    ieving
    0.10
    итай
    0.10
    есть
    0.09
    лаша
    0.09
    Activations Density 0.001%

    No Known Activations