Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131002
    Prev
    Next
    INDEX
    Explanations

    mathematical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ალურად
    -0.12
    -0.12
    Rhumela
    -0.12
     易乐
    -0.12
    <|reserved_200014|>
    -0.12
    期六合
    -0.12
     天天中彩票不能
    -0.12
    热这里只有精品
    -0.12
    【อ่านข้อความเต็ม
    -0.12
    çãeste
    -0.12
    POSITIVE LOGITS
     Quantity
    0.09
     parameter
    0.09
     Parameter
    0.08
     Length
    0.08
     Difference
    0.08
    Parameter
    0.08
     Power
    0.08
    Index
    0.08
    Power
    0.08
     Indicator
    0.08
    Activations Density 0.017%

    No Known Activations