Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19061
    Prev
    Next
    INDEX
    Explanations

    digital art and adobe

    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
     proponents
    -0.09
    isters
    -0.09
    each
    -0.09
    associated
    -0.08
    such
    -0.08
    episodes
    -0.08
    countries
    -0.08
    (_
    -0.08
    uders
    -0.08
    cić
    -0.08
    POSITIVE LOGITS
    -C
    0.09
    -ga
    0.08
    -j
    0.08
    -ph
    0.08
    -k
    0.08
    -tr
    0.08
    -c
    0.08
    -ক
    0.08
    -ה
    0.08
    -scal
    0.08
    Activations Density 0.022%

    No Known Activations