© 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. 31205
    Prev
    Next
    INDEX
    Explanations

    Java generics and wildcards

    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
    kara
    -0.08
     זמן
    -0.08
     карто
    -0.07
     карточ
    -0.07
     kvar
    -0.07
    카
    -0.07
     briefing
    -0.07
     asfalt
    -0.07
    kar
    -0.07
     asse
    -0.07
    POSITIVE LOGITS
     Sy
    0.08
     occurs
    0.07
    80
    0.07
    عا
    0.07
     Scoped
    0.07
     echtes
    0.07
    ocz
    0.07
    983
    0.07
    яч
    0.07
    _ylim
    0.07
    Activations Density 0.001%

    No Known Activations