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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130863
    Prev
    Next
    INDEX
    Explanations

    ,

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '])[
    -0.09
    adto
    -0.09
    ilee
    -0.08
    ・・・。↵↵
    -0.08
    itoare
    -0.08
     ></
    -0.07
    laublic
    -0.07
    ])[
    -0.07
    ומה
    -0.07
    lekileyo
    -0.07
    POSITIVE LOGITS
     because
    0.67
     since
    0.65
     क्योंकि
    0.60
    ,因为
    0.60
    since
    0.59
     eftersom
    0.58
    因为
    0.57
     karena
    0.57
    because
    0.57
     omdat
    0.57
    Activations Density 3.479%

    No Known Activations