© 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 EvalsExportsAPI 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. 69615
    Prev
    Next
    INDEX
    Explanations

    ·

    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
     ik
    -0.08
    cimento
    -0.08
     made
    -0.08
    品牌
    -0.07
     identifié
    -0.07
     reo
    -0.07
     cadence
    -0.07
    cement
    -0.07
     Oui
    -0.07
     wase
    -0.07
    POSITIVE LOGITS
    ატონ
    0.10
     გულ
    0.09
     სიტუ
    0.09
     ცხოვრება
    0.09
    怎么领
    0.09
    Misc
    0.09
     თან
    0.09
    ერ
    0.09
     განც
    0.09
     ისტორი
    0.09
    Activations Density 0.004%

    No Known Activations