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. 19417
    Prev
    Next
    INDEX
    Explanations

    and

    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
    's
    -0.09
    的天天
    -0.09
    ाच्या
    -0.09
     terrestr
    -0.08
    ేన
    -0.08
    的
    -0.08
    ుతున్న
    -0.08
    ावर
    -0.08
    noinspection
    -0.08
    ేని
    -0.07
    POSITIVE LOGITS
     outras
    0.09
     અન્ય
    0.08
     Heat
    0.08
     lòt
    0.08
     other
    0.08
     drugih
    0.08
     communications
    0.08
     sauran
    0.08
     ٻين
    0.08
    ndash
    0.08
    Activations Density 0.132%

    No Known Activations