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. 98216
    Prev
    Next
    INDEX
    Explanations

    ä

    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
     الكويت
    -0.09
     Или
    -0.08
    	or
    -0.08
    BY
    -0.08
     arba
    -0.08
     Kuid
    -0.08
     أو
    -0.08
     purge
    -0.08
     vagy
    -0.08
     البيان
    -0.08
    POSITIVE LOGITS
    .Last
    0.09
    .upper
    0.09
    ränkt
    0.08
    fasst
    0.08
    .Bad
    0.08
    .maximum
    0.08
    .fail
    0.08
    *num
    0.08
    .last
    0.07
    .cloud
    0.07
    Activations Density 0.005%

    No Known Activations