Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77490
    Prev
    Next
    INDEX
    Explanations

    1

    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
     comparatively
    -0.08
     weerstand
    -0.08
     möglichst
    -0.08
     twaalf
    -0.08
     zelf
    -0.08
     relativamente
    -0.08
     lembrar
    -0.08
     intuit
    -0.07
    λημα
    -0.07
    kwara
    -0.07
    POSITIVE LOGITS
    ino
    0.07
     Berd
    0.07
     uud
    0.07
    0.07
     pha
    0.07
     decree
    0.07
     structs
    0.07
    .goto
    0.06
    র্জ
    0.06
     oat
    0.06
    Activations Density 0.011%

    No Known Activations