© 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. 69472
    Prev
    Next
    INDEX
    Explanations

    nuts and/or typo "and"

    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
    love
    -0.08
     temperatur
    -0.07
     организма
    -0.07
     inherent
    -0.07
    عرف
    -0.07
     amore
    -0.07
     intrins
    -0.07
    તું
    -0.07
     imaginary
    -0.07
     hipot
    -0.07
    POSITIVE LOGITS
    چه
    0.09
     doubled
    0.08
    Shanghai
    0.08
     סוג
    0.08
    British
    0.08
    发表评论
    0.08
    Verbose
    0.08
    Half
    0.08
    Quarter
    0.08
     מוע
    0.08
    Activations Density 0.005%

    No Known Activations