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. 78
    Prev
    Next
    INDEX
    Explanations

    z

    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
    insatz
    -0.09
    鞋
    -0.09
     crate
    -0.08
    kob
    -0.08
    wane
    -0.08
    blok
    -0.07
    糕
    -0.07
     chaussures
    -0.07
     контей
    -0.07
    Ап
    -0.07
    POSITIVE LOGITS
     seven
    0.08
     leyes
    0.08
    法律
    0.07
    关于
    0.07
     ?><
    0.07
     federal
    0.07
     प्रधानम
    0.07
     الاول
    0.07
     seventeen
    0.07
     Senate
    0.07
    Activations Density 0.001%

    No Known Activations