© 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. 54910
    Prev
    Next
    INDEX
    Explanations

    all

    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
    είο
    -0.08
     vui
    -0.08
     viva
    -0.08
    AGR
    -0.07
     接
    -0.07
    553
    -0.07
    -vit
    -0.07
    ندا
    -0.07
    Adj
    -0.07
    ssc
    -0.07
    POSITIVE LOGITS
     ক্ষেত্রে
    0.09
     nor
    0.08
    地方
    0.08
     anymore
    0.08
     peligros
    0.08
     इसलिए
    0.08
     mandat
    0.08
     lief
    0.08
     الأحيان
    0.07
     necessarily
    0.07
    Activations Density 0.009%

    No Known Activations