© 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. 23-RESID-POST-AA
    11. 50461
    Prev
    Next
    INDEX
    Explanations

    professional in other 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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     config
    -0.09
    $config
    -0.08
     arithmetic
    -0.08
    NSString
    -0.07
     mosque
    -0.07
     tanaman
    -0.07
    .config
    -0.07
    字符串
    -0.07
    Arithmetic
    -0.07
     scriptures
    -0.07
    POSITIVE LOGITS
     professional
    0.77
     professionnel
    0.72
     profesional
    0.71
    Professional
    0.71
     profissional
    0.70
     Professional
    0.70
     professionnelle
    0.69
     профессион
    0.69
     professionele
    0.68
     profesionales
    0.68
    Activations Density 0.260%

    No Known Activations