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. 30556
    Prev
    Next
    INDEX
    Explanations

    triangulations

    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
     zgod
    -0.08
    uyer
    -0.08
     norme
    -0.08
    total
    -0.08
    nb
    -0.08
    YM
    -0.08
     LABEL
    -0.08
    agrama
    -0.08
     норм
    -0.07
    alternative
    -0.07
    POSITIVE LOGITS
    -earth
    0.09
    “大
    0.08
     grandi
    0.08
     convex
    0.08
    -dessus
    0.08
    "ל
    0.08
     vertex
    0.08
    黑人
    0.08
    -grand
    0.08
     fireworks
    0.08
    Activations Density 0.035%

    No Known Activations