© 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. 70928
    Prev
    Next
    INDEX
    Explanations

    面

    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
     Exeter
    -0.08
     За
    -0.08
     اقتصادی
    -0.08
     Exploring
    -0.07
     Brexit
    -0.07
    386
    -0.07
     exploring
    -0.07
     ope
    -0.07
    erging
    -0.07
     Hob
    -0.07
    POSITIVE LOGITS
    YYYY
    0.08
    格式
    0.08
    тө
    0.08
     titi
    0.08
    Formato
    0.08
     format
    0.07
     YYYY
    0.07
    ட்ச
    0.07
     formato
    0.07
     Sigue
    0.07
    Activations Density 0.006%

    No Known Activations