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. 43197
    Prev
    Next
    INDEX
    Explanations

    corporations

    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
    verse
    -0.08
     dec
    -0.08
     denom
    -0.07
    ipit
    -0.07
     denominator
    -0.07
     dold
    -0.07
     منز
    -0.07
     {
    -0.07
    ibre
    -0.07
     Speedway
    -0.07
    POSITIVE LOGITS
     inteira
    0.10
    -sponsored
    0.09
    信誉
    0.09
    -wide
    0.09
    /company
    0.09
    Official
    0.09
    団
    0.08
     자체
    0.08
    fani
    0.08
     Official
    0.08
    Activations Density 0.109%

    No Known Activations