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. 58558
    Prev
    Next
    INDEX
    Explanations

    Comparison

    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
     Gust
    -0.08
    树林
    -0.08
    木
    -0.07
     bomen
    -0.07
     તરફ
    -0.07
     Champ
    -0.07
    然而
    -0.07
    Wal
    -0.07
     verantwoordelijkheid
    -0.07
    ,大
    -0.07
    POSITIVE LOGITS
     तुलना
    0.09
     비교
    0.09
     Shipping
    0.08
     comparing
    0.08
     nhau
    0.08
     Comparing
    0.08
     срав
    0.08
    而言
    0.08
     Compare
    0.08
     benchmarks
    0.08
    Activations Density 0.051%

    No Known Activations