Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77188
    Prev
    Next
    INDEX
    Explanations

    CJ7

    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
     ovar
    -0.10
     parole
    -0.10
     Postsecondary
    -0.09
     cartes
    -0.09
     estadounidense
    -0.08
    Percentage
    -0.08
     americans
    -0.08
     amerik
    -0.08
     paroles
    -0.08
     rdr
    -0.08
    POSITIVE LOGITS
     Việt
    0.10
    广东
    0.09
    Myanmar
    0.09
     Guangzhou
    0.09
     Guangdong
    0.09
     Alibaba
    0.09
     Myanmar
    0.09
     创
    0.08
     福建
    0.08
    创
    0.08
    Activations Density 0.001%

    No Known Activations