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. 77247
    Prev
    Next
    INDEX
    Explanations

    steam

    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
     pleg
    -0.08
    981
    -0.08
     electoral
    -0.08
    withdraw
    -0.07
     পদ
    -0.07
     extremist
    -0.07
     alleg
    -0.07
    usize
    -0.07
     apostas
    -0.07
    osin
    -0.07
    POSITIVE LOGITS
     Гар
    0.09
     demora
    0.09
    สด
    0.09
    现场
    0.09
     hidr
    0.08
    来自
    0.08
     pluie
    0.08
    vura
    0.08
     Алар
    0.08
     generated
    0.08
    Activations Density 0.003%

    No Known Activations