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. 75909
    Prev
    Next
    INDEX
    Explanations

    quotes

    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
     Charity
    -0.08
    _eth
    -0.08
     Eth
    -0.08
     scout
    -0.08
     scouts
    -0.08
    Cath
    -0.08
    -night
    -0.08
     vertreten
    -0.07
    Eth
    -0.07
    Jessica
    -0.07
    POSITIVE LOGITS
    (cap
    0.09
    cap
    0.08
     `;↵
    0.08
    .Cap
    0.08
     RDC
    0.08
     interchange
    0.08
    riffe
    0.07
     кап
    0.07
     Cap
    0.07
    撑
    0.07
    Activations Density 0.001%

    No Known Activations