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. 11-RESID-POST-AA
    6. 12980
    Prev
    Next
    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دوب
    -0.08
     handen
    -0.08
    )value
    -0.07
     astroph
    -0.07
     نگ
    -0.07
     retrieving
    -0.07
    &(
    -0.07
     صح
    -0.07
     migraines
    -0.07
    VALUES
    -0.07
    POSITIVE LOGITS
     orb
    0.07
    usse
    0.07
     quen
    0.07
    _SELECTION
    0.07
    .quote
    0.07
    それ
    0.07
     ị
    0.07
     misión
    0.07
     Ministry
    0.07
     slave
    0.07
    Activations Density 0.021%

    No Known Activations