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. 43342
    Prev
    Next
    INDEX
    Explanations

    even numbers/squares

    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
     hanem
    -0.08
     Brief
    -0.07
    enzel
    -0.07
     Kindle
    -0.07
     imper
    -0.07
     Geb
    -0.07
     cidadão
    -0.07
    ramer
    -0.07
     Sath
    -0.07
     Edge
    -0.07
    POSITIVE LOGITS
    ୁ
    0.08
     lich
    0.08
    795
    0.08
    +l
    0.08
    িখ
    0.08
     frustrated
    0.08
    _SEL
    0.07
    ু
    0.07
    삼
    0.07
     зат
    0.07
    Activations Density 0.012%

    No Known Activations