© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    legal, accident compensation

    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
    cee
    -0.09
     nécessité
    -0.08
     intertw
    -0.08
     الحاجة
    -0.07
     iterative
    -0.07
    chein
    -0.07
    ạm
    -0.07
     purpose
    -0.07
    ：《
    -0.07
     need
    -0.07
    POSITIVE LOGITS
     refunds
    0.10
     récupération
    0.10
     guaranteed
    0.10
     страх
    0.10
    追回
    0.09
     выгод
    0.09
     получение
    0.09
     Guaranteed
    0.09
    待遇
    0.09
     récupérer
    0.09
    Activations Density 0.035%

    No Known Activations