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. 55971
    Prev
    Next
    INDEX
    Explanations

    call

    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
     이름
    -0.08
     mocha
    -0.08
     žele
    -0.07
     이렇게
    -0.07
     পদ
    -0.07
     Kamer
    -0.07
    兄
    -0.07
    aise
    -0.07
    早餐
    -0.07
     പാല
    -0.07
    POSITIVE LOGITS
     workforce
    0.10
     Workforce
    0.09
     inbound
    0.08
    Inbound
    0.08
     outsourced
    0.08
    Resumo
    0.08
    /text
    0.08
     batches
    0.08
    Texto
    0.08
     queued
    0.07
    Activations Density 0.008%

    No Known Activations