© 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. 94706
    Prev
    Next
    INDEX
    Explanations

    long jump

    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
     wiring
    -0.08
    .tint
    -0.08
     simmer
    -0.08
     جلد
    -0.07
     budgeting
    -0.07
    ڕ
    -0.07
     soups
    -0.07
    ⃣
    -0.07
    mart
    -0.07
    .billing
    -0.07
    POSITIVE LOGITS
     प्रतियोग
    0.11
     forbed
    0.10
     elo
    0.09
     impressive
    0.09
     улучш
    0.09
     improvement
    0.09
     соревн
    0.09
     луч
    0.09
     Athlete
    0.09
     verbessert
    0.09
    Activations Density 0.009%

    No Known Activations