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. 11-RESID-POST-AA
    6. 49111
    Prev
    Next
    INDEX
    Explanations

    shade

    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
     Ost
    -0.08
     Rong
    -0.08
    !!
    -0.08
     rese
    -0.07
     GMO
    -0.07
     !!
    -0.07
     gatherings
    -0.07
    !!!!!!!!
    -0.07
    314
    -0.07
     OECD
    -0.07
    POSITIVE LOGITS
    灰
    0.08
     shade
    0.08
     оттен
    0.08
    gray
    0.08
     shades
    0.08
    .water
    0.08
     gray
    0.07
    لاف
    0.07
    Mol
    0.07
     nuance
    0.07
    Activations Density 0.004%

    No Known Activations