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. 77238
    Prev
    Next
    INDEX
    Explanations

    conversational/instructional text

    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
     হার
    -0.08
     storms
    -0.07
    99
    -0.07
     हिस
    -0.07
     zwy
    -0.07
    圣
    -0.07
     stessa
    -0.07
    ادية
    -0.07
    compet
    -0.07
     Livro
    -0.07
    POSITIVE LOGITS
    node
    0.08
    ovor
    0.08
     guter
    0.08
     links
    0.07
     angeb
    0.07
    ుగు
    0.07
    pies
    0.07
    .node
    0.07
     ра
    0.07
     가지
    0.07
    Activations Density 1.081%

    No Known Activations