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. 113087
    Prev
    Next
    INDEX
    Explanations

    only

    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
    ców
    -0.09
    unun
    -0.08
    چې
    -0.08
     खोज
    -0.08
    issued
    -0.08
    Vol
    -0.08
    warehouse
    -0.08
     Mercer
    -0.08
    Farm
    -0.08
    isant
    -0.08
    POSITIVE LOGITS
     проп
    0.08
    ğiniz
    0.08
     ọna
    0.07
     หาก
    0.07
    してください
    0.07
     oxide
    0.07
    드시
    0.07
     keb
    0.07
     creativity
    0.07
     déb
    0.07
    Activations Density 0.005%

    No Known Activations