© 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. 43575
    Prev
    Next
    INDEX
    Explanations

    endpoint

    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
    143
    -0.08
     combating
    -0.08
    働
    -0.07
     Manchester
    -0.07
     folle
    -0.07
    tte
    -0.07
     pertinentes
    -0.07
    fact
    -0.07
    pp
    -0.07
    iyya
    -0.07
    POSITIVE LOGITS
    notes
    0.08
    적으로
    0.08
     Dexter
    0.08
    typen
    0.07
     sorpresa
    0.07
     சர
    0.07
     الأص
    0.07
    락
    0.07
     Legisl
    0.07
     ধরে
    0.07
    Activations Density 0.006%

    No Known Activations