© 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. 23-RESID-POST-AA
    11. 97793
    Prev
    Next
    INDEX
    Explanations

    ethnicity and race

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repairs
    -0.11
     nozzle
    -0.10
     trampoline
    -0.09
     teardown
    -0.09
     repair
    -0.09
     shutdown
    -0.09
     downtime
    -0.09
     Repairs
    -0.09
    .shutdown
    -0.09
     escrow
    -0.09
    POSITIVE LOGITS
     ethnicity
    0.28
     ethnic
    0.27
     minorities
    0.24
     racial
    0.24
     nationality
    0.23
    民族
    0.23
    Nationality
    0.22
    racial
    0.21
     religions
    0.21
     immigrants
    0.20
    Activations Density 0.371%

    No Known Activations