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. 60670
    Prev
    Next
    INDEX
    Explanations

    code

    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
     demor
    -0.08
     Advantage
    -0.08
     Suzanne
    -0.07
     Па
    -0.07
     吴
    -0.07
     Beispiele
    -0.07
     traur
    -0.07
     Examples
    -0.07
     情
    -0.07
     Año
    -0.07
    POSITIVE LOGITS
     trong
    0.10
     everywhere
    0.09
     elsewhere
    0.09
     überall
    0.08
     místo
    0.08
     oblasti
    0.08
    /navbar
    0.08
     lutar
    0.08
     размест
    0.08
     opnemen
    0.08
    Activations Density 0.014%

    No Known Activations