© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68667
    Prev
    Next
    INDEX
    Explanations

    AI chatbot behavior

    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
     genetically
    -0.09
    Brook
    -0.09
     fjár
    -0.08
     renovations
    -0.08
     আয়োজন
    -0.08
     recruitment
    -0.08
     reformas
    -0.08
     migrating
    -0.08
     recruits
    -0.08
    采购
    -0.08
    POSITIVE LOGITS
     conversational
    0.13
    回答
    0.12
     GPT
    0.11
     प्रदान
    0.11
     ارائه
    0.11
     پاسخ
    0.10
     Providing
    0.10
     ответы
    0.10
     Markdown
    0.10
     Assistant
    0.10
    Activations Density 0.040%

    No Known Activations