© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 31009
    Prev
    Next
    INDEX
    Explanations

    Italian Restaurants

    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
     thunk
    -0.08
    概要
    -0.08
    umming
    -0.07
     displacement
    -0.07
     phosphorylation
    -0.07
    	typedef
    -0.07
     μό
    -0.07
    ��
    -0.07
     Completion
    -0.07
     enthusiasm
    -0.07
    POSITIVE LOGITS
     업체
    0.09
    ร้าน
    0.09
    店
    0.09
    字号
    0.09
     réput
    0.09
    彩票站
    0.09
     ร้าน
    0.09
    投注站
    0.09
     प्रतिष्ठ
    0.08
    煌
    0.08
    Activations Density 0.027%

    No Known Activations