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. 39
    Prev
    Next
    INDEX
    Explanations

    assignment

    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
     berbagai
    -0.09
     большин
    -0.09
     современные
    -0.09
     исполнитель
    -0.08
    phäre
    -0.08
     представители
    -0.08
    stöðu
    -0.08
     bruke
    -0.08
    iñ
    -0.08
     կողմ
    -0.08
    POSITIVE LOGITS
     wanting
    0.11
     we're
    0.10
     you're
    0.09
     wants
    0.09
     vậy
    0.09
    正在
    0.08
     chce
    0.08
     asking
    0.08
     someone's
    0.08
     I'm
    0.08
    Activations Density 0.015%

    No Known Activations