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. 98473
    Prev
    Next
    INDEX
    Explanations

    hành

    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
    ftware
    -0.09
    idae
    -0.09
    aneously
    -0.08
    َى
    -0.08
    imum
    -0.07
    enerated
    -0.07
    文字
    -0.07
    antiated
    -0.07
    疾病
    -0.07
    า�
    -0.07
    POSITIVE LOGITS
     vi
    0.09
    動
    0.09
    보
    0.08
     schnellen
    0.08
    动
    0.08
    ਵ
    0.08
     entsprechenden
    0.08
     động
    0.08
     xử
    0.08
    0.08
    Activations Density 0.003%

    No Known Activations