© 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. 11-RESID-POST-AA
    11. 114249
    Prev
    Next
    INDEX
    Explanations

    different writing styles

    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
     наиболее
    -0.08
     بي
    -0.08
     ضرور
    -0.08
     کئے
    -0.08
     árbit
    -0.08
     najbardziej
    -0.08
     najwięks
    -0.07
     bung
    -0.07
     پاب
    -0.07
     paquetes
    -0.07
    POSITIVE LOGITS
    vente
    0.08
    0.08
    pivot
    0.08
     onmiddell
    0.07
    consume
    0.07
     eto
    0.07
    resolve
    0.07
    classic
    0.07
       ↵↵
    0.07
    gling
    0.07
    Activations Density 0.053%
    No Known Activations