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. 76038
    Prev
    Next
    INDEX
    Explanations

    chance, randomness, serendipity

    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
     PV
    -0.08
     coolant
    -0.08
     PAR
    -0.08
     Lava
    -0.07
     pound
    -0.07
     Trou
    -0.07
    etc
    -0.07
     보기
    -0.07
    Unified
    -0.07
    uelta
    -0.07
    POSITIVE LOGITS
     hasard
    0.12
     discoveries
    0.10
    =random
    0.10
    偶
    0.10
    /random
    0.10
     stumbled
    0.10
     azar
    0.09
     chance
    0.09
    .randint
    0.09
    .random
    0.09
    Activations Density 0.017%

    No Known Activations