© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65316
    Prev
    Next
    INDEX
    Explanations

    front

    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
     dos
    -0.09
     livelihood
    -0.08
     União
    -0.08
    ardu
    -0.07
    ුණු
    -0.07
     incentives
    -0.07
     prog
    -0.07
    dos
    -0.07
     schemas
    -0.07
     komand
    -0.07
    POSITIVE LOGITS
    /back
    0.08
     Leroy
    0.08
     frustr
    0.08
     llor
    0.08
     Booking
    0.08
     Geometry
    0.07
    GLISH
    0.07
     solver
    0.07
     pierwszy
    0.07
     sijait
    0.07
    Activations Density 0.002%

    No Known Activations