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. 106138
    Prev
    Next
    INDEX
    Explanations

    goods

    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
     Indianapolis
    -0.08
    ’om
    -0.08
     predecessor
    -0.08
    ապատ
    -0.08
     appunt
    -0.08
    omorphic
    -0.08
     Babies
    -0.08
     ome
    -0.07
    stahl
    -0.07
     natuur
    -0.07
    POSITIVE LOGITS
    gia
    0.09
    .goods
    0.09
    goods
    0.09
    Goods
    0.08
     goods
    0.08
    0.08
    icol
    0.07
     pamam
    0.07
    /category
    0.07
    plates
    0.07
    Activations Density 0.004%

    No Known Activations