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. 53994
    Prev
    Next
    INDEX
    Explanations

    externally

    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
     quibus
    -0.08
    érie
    -0.08
     adgang
    -0.08
     Responses
    -0.08
    Spent
    -0.08
     देर
    -0.08
     يقل
    -0.08
     accès
    -0.08
     الأسبوع
    -0.08
     klubb
    -0.08
    POSITIVE LOGITS
    邪
    0.09
     coexist
    0.08
     nhau
    0.08
     서로
    0.08
     തമ്മ
    0.08
    尾
    0.08
     handshake
    0.08
     gegense
    0.08
    融合
    0.08
    之间
    0.08
    Activations Density 0.017%

    No Known Activations