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. 11-RESID-POST-AA
    6. 75947
    Prev
    Next
    INDEX
    Explanations

    triathlon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solamente
    -0.08
     HU
    -0.08
    Hg
    -0.08
    Hu
    -0.08
    etermin
    -0.07
     describ
    -0.07
     hir
    -0.07
     केवल
    -0.07
     alleen
    -0.07
     áp
    -0.07
    POSITIVE LOGITS
    طرق
    0.09
     voyages
    0.08
     journeys
    0.08
    corator
    0.08
     Tacoma
    0.08
    jóða
    0.08
    ုတ္
    0.08
    vedra
    0.08
    ятель
    0.08
    _Server
    0.08
    Activations Density 0.001%

    No Known Activations