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. 17
    Prev
    Next
    INDEX
    Explanations

    practice

    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
     consortium
    -0.08
    -information
    -0.08
     государ
    -0.08
     размещ
    -0.08
     расположен
    -0.08
    etag
    -0.08
    director
    -0.08
     предостав
    -0.07
    blica
    -0.07
    -contained
    -0.07
    POSITIVE LOGITS
    练
    0.24
     പരിശീല
    0.21
     oefenen
    0.21
    训练
    0.19
     training
    0.18
     प्रशिक्षण
    0.18
     practicing
    0.18
     latihan
    0.18
     luyện
    0.18
     mastering
    0.17
    Activations Density 0.081%

    No Known Activations