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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7629
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     unle
    -0.09
    ள்ள
    -0.08
     wk
    -0.07
     kak
    -0.07
     unleash
    -0.07
     ticker
    -0.07
    ृतिक
    -0.07
     فق
    -0.07
    ेरी
    -0.07
     immature
    -0.07
    POSITIVE LOGITS
     compon
    0.07
     noodles
    0.07
     chees
    0.07
    ્યાન
    0.07
    િત
    0.07
    ights
    0.07
    ناول
    0.07
    乘
    0.07
     thoughtfully
    0.07
    0.07
    Activations Density 0.042%
    No Known Activations