Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19392
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ample
    -0.10
     indul
    -0.09
     خواهند
    -0.09
     großzüg
    -0.09
     indulge
    -0.09
     generous
    -0.09
    �
    -0.09
     خواهد
    -0.08
    utang
    -0.08
     indulg
    -0.08
    POSITIVE LOGITS
     ისე
    0.10
     ώστε
    0.10
    ?
    0.10
    ?↵↵
    0.09
     чтоб
    0.09
     добиться
    0.09
     verhindern
    0.09
    ,希望
    0.09
     efficiently
    0.09
     કરવા
    0.09
    Activations Density 0.075%

    No Known Activations