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. 42978
    Prev
    Next
    INDEX
    Explanations

    United Kingdom royalty

    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
     typical
    -0.08
     IP
    -0.08
     darr
    -0.08
     l
    -0.08
     vy
    -0.08
    Due
    -0.07
    _To
    -0.07
     बढ
    -0.07
    Ip
    -0.07
     बाज
    -0.07
    POSITIVE LOGITS
     monarchy
    0.10
     الحالي
    0.08
     Majesty
    0.08
     JLabel
    0.08
    皇
    0.08
     peacefully
    0.08
     Chalet
    0.08
     conna
    0.08
    平成
    0.07
     hard
    0.07
    Activations Density 0.023%

    No Known Activations