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. 19383
    Prev
    Next
    INDEX
    Explanations

    half

    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
    174
    -0.09
    (bg
    -0.08
    /bg
    -0.08
     నేప
    -0.08
     multicultural
    -0.08
     multilingual
    -0.08
     zak
    -0.08
    赚钱
    -0.08
     oku
    -0.08
     hakuna
    -0.07
    POSITIVE LOGITS
    -half
    0.12
    씩
    0.10
    份
    0.10
    -way
    0.10
    -hearted
    0.09
    -field
    0.09
    -year
    0.09
    -step
    0.09
    -thirds
    0.08
    -right
    0.08
    Activations Density 0.030%

    No Known Activations