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. 111808
    Prev
    Next
    INDEX
    Explanations

    through

    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
    (sign
    -0.09
    ాంక
    -0.09
     inherently
    -0.08
     기술
    -0.08
    tev
    -0.08
    ()?
    -0.08
     왜
    -0.08
    _Unity
    -0.08
    _sign
    -0.07
    צ
    -0.07
    POSITIVE LOGITS
     shutters
    0.10
     hills
    0.10
    好友
    0.10
     shutter
    0.08
    医院
    0.08
    挡
    0.08
     Williamsburg
    0.08
    窗
    0.08
     pharmacies
    0.08
     colorful
    0.08
    Activations Density 0.008%

    No Known Activations