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. 106188
    Prev
    Next
    INDEX
    Explanations

    zu

    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
    須
    -0.09
    即可
    -0.09
    Tours
    -0.08
     Tort
    -0.08
    mnt
    -0.08
    SSL
    -0.08
    ifficulty
    -0.07
    须
    -0.07
    Org
    -0.07
    lll
    -0.07
    POSITIVE LOGITS
     көтер
    0.08
     faire
    0.08
     kre
    0.08
     ş
    0.08
     mettre
    0.08
    //↵//
    0.08
     embed
    0.08
    γει
    0.08
     thabhairt
    0.08
    ittää
    0.07
    Activations Density 0.014%

    No Known Activations