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. 130786
    Prev
    Next
    INDEX
    Explanations

    必

    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
    itulo
    -0.10
     ona
    -0.08
    anner
    -0.08
     afirm
    -0.07
    jalan
    -0.07
    agne
    -0.07
    ahayag
    -0.07
    acket
    -0.07
    imoto
    -0.07
    ја
    -0.07
    POSITIVE LOGITS
    需
    0.13
    备用
    0.12
    备
    0.12
    不可
    0.12
     修
    0.11
    修
    0.11
    備
    0.10
     კრ
    0.09
     做
    0.09
     backup
    0.09
    Activations Density 0.001%

    No Known Activations