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. 106097
    Prev
    Next
    INDEX
    Explanations

    percent

    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
     пух
    -0.08
     Titan
    -0.08
     Variety
    -0.08
     Folk
    -0.08
     Forum
    -0.08
    вар
    -0.07
     radios
    -0.07
    oldo
    -0.07
     Abl
    -0.07
     Chronicle
    -0.07
    POSITIVE LOGITS
     desn
    0.09
    itize
    0.08
    oque
    0.08
    ertificate
    0.08
     significa
    0.08
     betekent
    0.08
     quantify
    0.07
    ysters
    0.07
     zichzelf
    0.07
    (Rel
    0.07
    Activations Density 0.012%

    No Known Activations