Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45017
    Prev
    Next
    INDEX
    Explanations

    period

    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
     промеж
    -0.08
    .Results
    -0.08
    (results
    -0.08
    туу
    -0.07
    פן
    -0.07
    	Item
    -0.07
     неправ
    -0.07
     portion
    -0.07
    	results
    -0.07
     lad
    -0.07
    POSITIVE LOGITS
    deposit
    0.08
     channels
    0.07
    ✨
    0.07
    تص
    0.07
    渠道
    0.07
     pote
    0.07
     ¡
    0.07
    ️
    0.07
    wiz
    0.07
    ✅
    0.07
    Activations Density 0.041%

    No Known Activations