© 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. 19-RESID-POST-AA
    11. 102260
    Prev
    Next
    INDEX
    Explanations

    -American nationalities

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     旺
    -0.09
     Пров
    -0.08
     Президенти
    -0.08
    ziger
    -0.08
     KPI
    -0.08
     وزیراع
    -0.08
     نیرو
    -0.08
    扒开
    -0.08
     نظام
    -0.08
     मुख्यमंत्री
    -0.08
    POSITIVE LOGITS
    -American
    0.23
    -Americans
    0.20
     American
    0.19
    American
    0.18
     Canadian
    0.17
     Americans
    0.17
     അമേരിക്ക
    0.17
    加拿大
    0.17
     अमेरिक
    0.16
     immigrant
    0.16
    Activations Density 0.019%

    No Known Activations