Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60845
    Prev
    Next
    INDEX
    Explanations

    Ghettos and discrimination

    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
    keer
    -0.08
    ائلة
    -0.08
     chanc
    -0.08
     Consultants
    -0.08
    gevity
    -0.07
    มาก
    -0.07
    력이
    -0.07
     Pence
    -0.07
     الجهات
    -0.07
     panne
    -0.07
    POSITIVE LOGITS
     vivir
    0.08
    生活
    0.08
    填
    0.08
     gyven
    0.08
     vivere
    0.08
     dzī
    0.07
    Living
    0.07
     living
    0.07
    living
    0.07
     vivent
    0.07
    Activations Density 0.006%

    No Known Activations