© 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. 69881
    Prev
    Next
    INDEX
    Explanations

    weight

    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
     sociedades
    -0.08
    .dao
    -0.08
     incompet
    -0.08
     toegepast
    -0.07
    Periods
    -0.07
    -а
    -0.07
     Admissions
    -0.07
    。那么
    -0.07
     perguntas
    -0.07
     prosper
    -0.07
    POSITIVE LOGITS
     الوزن
    0.15
    重量
    0.15
     वजन
    0.13
     lightweight
    0.13
    weight
    0.12
     وزن
    0.12
     ഭാര
    0.12
     Lightweight
    0.12
    軽
    0.11
    _weight
    0.11
    Activations Density 0.052%

    No Known Activations