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. 15-RESID-POST-AA
    6. 16
    Prev
    Next
    INDEX
    Explanations

    delete

    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
    illum
    -0.08
     chegada
    -0.07
    交流
    -0.07
     prestar
    -0.07
    ائح
    -0.07
     rise
    -0.07
    Lighting
    -0.07
    ’agit
    -0.07
     crest
    -0.07
    peek
    -0.07
    POSITIVE LOGITS
     删除
    0.19
    掉
    0.19
    删除
    0.18
    (Delete
    0.18
    (delete
    0.17
     삭제
    0.17
     löschen
    0.17
     Deletes
    0.16
    .Delete
    0.16
    	Delete
    0.16
    Activations Density 0.019%

    No Known Activations