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. 44951
    Prev
    Next
    INDEX
    Explanations

    Hearts

    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
     Eagle
    -0.08
     Scots
    -0.08
    arro
    -0.08
    дзя
    -0.08
     hielt
    -0.07
     atentos
    -0.07
    xdb
    -0.07
    ifestyle
    -0.07
    memor
    -0.07
     aufgenommen
    -0.07
    POSITIVE LOGITS
    URLs
    0.09
    URI
    0.08
    niet
    0.08
    &&(
    0.08
     sac
    0.08
     sâu
    0.08
     lotteries
    0.08
    /access
    0.08
     وكيف
    0.07
     ইউনিয়
    0.07
    Activations Density 0.000%

    No Known Activations