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. 58753
    Prev
    Next
    INDEX
    Explanations

    bound

    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
     inicia
    -0.08
     despe
    -0.08
     aborda
    -0.08
     Ple
    -0.07
     assin
    -0.07
     chef
    -0.07
     storm
    -0.07
    eres
    -0.07
    Wow
    -0.07
     damn
    -0.07
    POSITIVE LOGITS
     사항
    0.08
     délais
    0.08
     �
    0.08
    imum
    0.07
     �
    0.07
    ary
    0.07
    詞
    0.07
    とな
    0.07
    เหล
    0.07
    ด้าน
    0.07
    Activations Density 0.006%

    No Known Activations