© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18488
    Prev
    Next
    INDEX
    Explanations

    doctors/medical in different languages

    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
    瞬
    -0.09
    Compact
    -0.08
     exploded
    -0.08
     fake
    -0.07
     Marble
    -0.07
     erzeug
    -0.07
     Instant
    -0.07
     explode
    -0.07
     Fake
    -0.07
     Compact
    -0.07
    POSITIVE LOGITS
    医生
    0.24
     மருத்த
    0.23
     پزش
    0.23
     врач
    0.22
    咨询
    0.22
     डॉक्टर
    0.21
     الطبيب
    0.21
     dokter
    0.21
     physician
    0.20
     consultation
    0.20
    Activations Density 0.032%

    No Known Activations