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. 43948
    Prev
    Next
    INDEX
    Explanations

    vase

    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
    upiter
    -0.08
     voy
    -0.08
     hambre
    -0.07
    leng
    -0.07
     lender
    -0.07
     Lumber
    -0.07
    vest
    -0.07
    epsilon
    -0.07
    arsch
    -0.07
     યુ
    -0.07
    POSITIVE LOGITS
     центре
    0.08
    丁香
    0.08
     ngoài
    0.08
    दार
    0.08
    罗斯
    0.08
     miest
    0.08
     floral
    0.08
     chic
    0.08
    .alibaba
    0.08
     декоратив
    0.08
    Activations Density 0.003%

    No Known Activations