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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26184
    Prev
    Next
    INDEX
    Explanations

    segregation

    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
     Bachelor's
    -0.08
    brica
    -0.08
     szab
    -0.08
     partea
    -0.08
     bachelor's
    -0.08
     interns
    -0.08
     Says
    -0.07
    ന്റെ
    -0.07
     internos
    -0.07
     Internal
    -0.07
    POSITIVE LOGITS
     segregation
    0.12
     concentration
    0.11
     concentrations
    0.10
     segreg
    0.10
     Concentr
    0.09
     concentr
    0.09
     zoning
    0.09
    迁
    0.09
     concentração
    0.09
     concentrated
    0.09
    Activations Density 0.009%

    No Known Activations