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. 48
    Prev
    Next
    INDEX
    Explanations

    image file types

    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
     olmaz
    -0.09
     także
    -0.08
     również
    -0.08
    なので
    -0.08
     επίσης
    -0.08
     også
    -0.08
     $("
    -0.08
     loose
    -0.08
     také
    -0.08
     أيضًا
    -0.08
    POSITIVE LOGITS
    .png
    0.11
    .svg
    0.10
    .jpg
    0.10
    .gif
    0.09
    .jpeg
    0.09
     диаг
    0.09
     depicted
    0.09
    .PNG
    0.08
     silhouette
    0.08
    _c
    0.08
    Activations Density 0.035%

    No Known Activations