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. 98405
    Prev
    Next
    INDEX
    Explanations

    unknown token

    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
    发动
    -0.08
    姓名
    -0.08
    容
    -0.08
     boli
    -0.08
    名称
    -0.08
    剧情
    -0.08
    ,name
    -0.08
    傳
    -0.07
     القيادة
    -0.07
    發
    -0.07
    POSITIVE LOGITS
    �
    0.10
     Aw
    0.08
    ্রি
    0.08
     sought
    0.08
     оз
    0.08
    Aw
    0.07
    affirm
    0.07
    Aff
    0.07
    Impro
    0.07
     Oder
    0.07
    Activations Density 0.000%

    No Known Activations