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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 46
    Prev
    Next
    INDEX
    Explanations

    formatting

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ímav
    -0.09
    еспондент
    -0.09
    ӯст
    -0.08
    епутат
    -0.08
    უც
    -0.08
    Cov
    -0.08
    ាតិ
    -0.08
     öndür
    -0.08
     представитель
    -0.08
    эзід
    -0.08
    POSITIVE LOGITS
     neat
    0.08
     guidelines
    0.08
    规定
    0.08
    :↵↵
    0.08
     formula
    0.08
     नियम
    0.08
    规范
    0.08
    格式
    0.08
     formatting
    0.07
     acuerdo
    0.07
    Activations Density 0.006%

    No Known Activations