© 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. 30904
    Prev
    Next
    INDEX
    Explanations

    relativistic cosmology

    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
     Erd
    -0.08
    艺术
    -0.08
     fountain
    -0.08
     الرجل
    -0.08
    andishi
    -0.08
    藝術
    -0.08
     Sherlock
    -0.08
    jas
    -0.07
     غو
    -0.07
    .FONT
    -0.07
    POSITIVE LOGITS
     inflation
    0.08
     economy
    0.08
     expansion
    0.08
     diet
    0.07
    (T
    0.07
     dehydr
    0.07
     dyd
    0.07
     trovi
    0.07
     dehydration
    0.07
     cooker
    0.07
    Activations Density 0.001%

    No Known Activations