© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    file paths

    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
    _sampler
    -0.10
     නම්
    -0.09
     মন্তব্য
    -0.08
     hasard
    -0.08
     వ్యాఖ్య
    -0.08
     comentarios
    -0.07
     sampler
    -0.07
     remar
    -0.07
    (arr
    -0.07
    antes
    -0.07
    POSITIVE LOGITS
    sandbox
    0.09
    filesystem
    0.09
     filesystem
    0.09
    沙
    0.09
     sandbox
    0.09
    omgeving
    0.09
     isolates
    0.08
     circumvent
    0.08
     staging
    0.08
    隔
    0.08
    Activations Density 0.007%

    No Known Activations