© 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. 48039
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Moodle
    -0.09
     Sinhala
    -0.09
     Indonesian
    -0.08
     coth
    -0.08
     MSc
    -0.08
     Vietnamese
    -0.08
     coqu
    -0.08
     Madagas
    -0.08
     Khmer
    -0.07
    ändig
    -0.07
    POSITIVE LOGITS
     nationwide
    0.16
    全国
    0.15
     федераль
    0.15
     전국
    0.15
     全国
    0.15
     federal
    0.15
     interstate
    0.15
     Nationwide
    0.14
    Federal
    0.13
    ，全国
    0.13
    Activations Density 0.260%

    No Known Activations