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. 23-RESID-POST-AA
    6. 98256
    Prev
    Next
    INDEX
    Explanations

    separators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .selenium
    -0.08
     метро
    -0.08
     обязатель
    -0.08
     espion
    -0.08
     Insol
    -0.08
    arant
    -0.08
     spider
    -0.08
     केस
    -0.07
    =count
    -0.07
    網
    -0.07
    POSITIVE LOGITS
     fatty
    0.13
     poissons
    0.11
     fish
    0.11
    鱼
    0.10
    ปลา
    0.10
    肥
    0.09
     peces
    0.09
    Fat
    0.09
    鱼儿
    0.09
    Cold
    0.09
    Activations Density 0.001%

    No Known Activations