© 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. 78089
    Prev
    Next
    INDEX
    Explanations

    melatonin

    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
     striker
    -0.08
     elbow
    -0.08
     اقتصادی
    -0.08
     참
    -0.07
    .Redis
    -0.07
    ="#">↵
    -0.07
     δι
    -0.07
     وسی
    -0.07
     Aless
    -0.07
     مناف
    -0.07
    POSITIVE LOGITS
     vitamin
    0.08
     bedtime
    0.08
    (calendar
    0.08
     bonita
    0.08
     instalada
    0.08
     photons
    0.08
    Wallpaper
    0.08
     cot
    0.08
     evenings
    0.07
    睡
    0.07
    Activations Density 0.002%

    No Known Activations