Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45700
    Prev
    Next
    INDEX
    Explanations

    white

    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
    meteor
    -0.09
     ech
    -0.08
     mande
    -0.08
    기의
    -0.08
    IBOutlet
    -0.07
     cafeteria
    -0.07
    nerie
    -0.07
     není
    -0.07
    cccc
    -0.07
     eggs
    -0.07
    POSITIVE LOGITS
    摘要
    0.09
    .publish
    0.08
    函
    0.08
     chapitre
    0.08
     heavyweight
    0.08
     detailing
    0.08
    章
    0.08
    发布
    0.08
     Pv
    0.08
    可信
    0.08
    Activations Density 0.010%

    No Known Activations