© 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. 23-RESID-POST-AA
    11. 97318
    Prev
    Next
    INDEX
    Explanations

    medical

    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
     Nutrition
    -0.10
     Patients
    -0.09
     pacientes
    -0.09
     Algebra
    -0.09
     termites
    -0.09
     poudre
    -0.09
     Vaccine
    -0.09
     Vacc
    -0.09
     Preschool
    -0.09
     pacient
    -0.09
    POSITIVE LOGITS
     medical
    0.41
    医疗
    0.37
     medische
    0.37
     médicale
    0.34
     medizin
    0.34
     médical
    0.33
    medical
    0.32
     медицин
    0.32
    Medical
    0.31
     의료
    0.31
    Activations Density 0.087%

    No Known Activations