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. 53889
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    .ch
    -0.08
     solder
    -0.07
     UTC
    -0.07
     fungerar
    -0.07
     ವಿಶ್ವ
    -0.07
     inti
    -0.07
    جلة
    -0.07
    -full
    -0.07
     provided
    -0.07
    -j
    -0.07
    POSITIVE LOGITS
     Vo
    0.08
    Vo
    0.08
     vet
    0.07
    wesen
    0.07
    subjects
    0.07
     tending
    0.07
     বিষয়
    0.07
     concentrating
    0.07
    ્ત
    0.07
     geen
    0.07
    Activations Density 0.003%

    No Known Activations