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. 56132
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     вык
    -0.08
     Nol
    -0.07
     CN
    -0.07
     HC
    -0.07
     SAS
    -0.07
     heavy
    -0.07
    LOC
    -0.07
     Vy
    -0.07
     Novembre
    -0.07
     নভেম্বর
    -0.07
    POSITIVE LOGITS
     prag
    0.09
     Dorothy
    0.09
     Colleges
    0.09
    .Is
    0.08
    民主
    0.08
     suburban
    0.08
    .Are
    0.08
    委员
    0.08
    ία
    0.08
    [,]
    0.08
    Activations Density 0.012%

    No Known Activations