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. 7-RESID-POST-AA
    6. 131045
    Prev
    Next
    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ordinarily
    -0.08
     wit
    -0.07
     Walmart
    -0.07
     pent
    -0.07
    وتر
    -0.07
     konkre
    -0.07
    لیم
    -0.07
    经营
    -0.07
     voork
    -0.07
     motivation
    -0.07
    POSITIVE LOGITS
    抽
    0.08
    utz
    0.08
    inga
    0.08
     whereby
    0.07
    528
    0.07
    oub
    0.07
    .kode
    0.07
     onderstaande
    0.07
     താഴ
    0.07
    gyro
    0.07
    Activations Density 0.002%

    No Known Activations