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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 88071
    Prev
    Next
    INDEX
    Explanations

    -word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    root
    -0.08
    .root
    -0.07
     √
    -0.07
     monitor
    -0.07
     milho
    -0.07
     sqrt
    -0.07
     mission
    -0.07
     root
    -0.07
     In
    -0.07
    jit
    -0.07
    POSITIVE LOGITS
     тез
    0.09
    Excerpt
    0.09
     расска
    0.09
    _RS
    0.09
     рассказ
    0.09
     пе
    0.09
    프트
    0.09
     посвящ
    0.08
    Cet
    0.08
    �
    0.08
    Activations Density 0.013%

    No Known Activations