© 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. 64327
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    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
    liye
    -0.09
    确认
    -0.08
     دين
    -0.08
     sedi
    -0.08
     принять
    -0.08
    itto
    -0.08
     прилож
    -0.08
     undertake
    -0.08
     أيض
    -0.08
    ണ്ഡ
    -0.07
    POSITIVE LOGITS
    However
    0.08
     geeignet
    0.08
    Suitable
    0.08
    /artificial
    0.08
    hang
    0.08
     constructions
    0.08
    count
    0.07
     Suitable
    0.07
     Would
    0.07
     achieves
    0.07
    Activations Density 0.053%

    No Known Activations