© 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. 15-RESID-POST-AA
    11. 16532
    Prev
    Next
    INDEX
    Explanations

    ifying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     போன்ற
    -0.08
     beauties
    -0.08
     وغيرها
    -0.08
    など
    -0.08
    etas
    -0.08
    ząt
    -0.08
     быць
    -0.08
    -Spiel
    -0.07
     ähn
    -0.07
     cag
    -0.07
    POSITIVE LOGITS
    oles
    0.08
    .d
    0.08
     द
    0.08
    вэл
    0.08
    министр
    0.07
     respecto
    0.07
     '='
    0.07
    关于
    0.07
    говор
    0.07
     hierover
    0.07
    Activations Density 0.097%

    No Known Activations