© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 79150
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
    .ee
    -0.09
     cửa
    -0.08
     എം
    -0.08
     eme
    -0.08
     Scandinavian
    -0.08
     Dres
    -0.07
    imizin
    -0.07
    Means
    -0.07
    人与
    -0.07
     Em
    -0.07
    POSITIVE LOGITS
     unge
    0.08
    ikh
    0.08
     ?>>
    0.08
     multiplication
    0.07
     البعض
    0.07
    nachten
    0.07
     sinful
    0.07
    Мен
    0.07
     gelöscht
    0.07
    युक्त
    0.07
    Activations Density 0.071%

    No Known Activations