© 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. 95867
    Prev
    Next
    INDEX
    Explanations

    legal/regulatory requirements

    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
     chatted
    -0.09
    -chat
    -0.09
    .chat
    -0.09
     drank
    -0.09
     chats
    -0.09
     Podcasts
    -0.09
     écouter
    -0.09
     чат
    -0.08
     chat
    -0.08
    聊天
    -0.08
    POSITIVE LOGITS
    法规
    0.22
     regulations
    0.21
    法律
    0.19
     réglementation
    0.19
     Regulations
    0.18
     legally
    0.18
     законодательства
    0.18
     réglement
    0.17
     regulament
    0.17
     कानून
    0.17
    Activations Density 0.411%

    No Known Activations