© 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. 19-RESID-POST-AA
    11. 102928
    Prev
    Next
    INDEX
    Explanations

    new

    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
     ұйымда
    -0.09
     आयोजना
    -0.09
     کوچ
    -0.08
     encargado
    -0.08
     challeng
    -0.08
    چے
    -0.08
     Organización
    -0.08
     timetable
    -0.08
    _Enable
    -0.08
     organizers
    -0.08
    POSITIVE LOGITS
     trend
    0.09
     invention
    0.09
     tendência
    0.08
     invented
    0.08
     craze
    0.08
     multit
    0.08
     Trend
    0.08
    方法
    0.08
     coined
    0.08
     looph
    0.08
    Activations Density 0.003%

    No Known Activations