© 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. 112739
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     approaches
    -0.09
    Beer
    -0.07
    PCM
    -0.07
    idon
    -0.07
     pim
    -0.07
    Applicant
    -0.07
    Rose
    -0.07
    Validator
    -0.07
     exert
    -0.07
     notions
    -0.07
    POSITIVE LOGITS
     totaling
    0.10
     слой
    0.09
     Hälfte
    0.09
     tulisan
    0.09
     полов
    0.09
     その他
    0.08
     tambahan
    0.08
     kategori
    0.08
     catégorie
    0.08
     Brit
    0.08
    Activations Density 0.066%

    No Known Activations