© 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. 111191
    Prev
    Next
    INDEX
    Explanations

    break

    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
     аспект
    -0.08
     ray
    -0.07
     van
    -0.07
    fæ
    -0.07
     Ver
    -0.07
     intimidating
    -0.07
    ตี
    -0.07
     desconoc
    -0.07
     statistik
    -0.07
    -def
    -0.07
    POSITIVE LOGITS
     মাঝে
    0.09
     refreshments
    0.09
    /stretch
    0.09
     snacks
    0.08
     વિર
    0.08
     teas
    0.08
     refreshed
    0.08
     rinse
    0.08
    inje
    0.08
     Contudo
    0.08
    Activations Density 0.010%

    No Known Activations