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. 11-RESID-POST-AA
    6. 77121
    Prev
    Next
    INDEX
    Explanations

    tic-tac-toe

    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
     daylight
    -0.08
    olidays
    -0.08
    loom
    -0.08
     Linux
    -0.08
     atl
    -0.07
    ffer
    -0.07
    topia
    -0.07
    scroll
    -0.07
     pilgrimage
    -0.07
    ality
    -0.07
    POSITIVE LOGITS
    棋
    0.12
     જીત
    0.11
     ganador
    0.11
    赢家
    0.11
    双方
    0.11
     побед
    0.10
     vencedor
    0.10
     tic
    0.10
     partisan
    0.10
     जीत
    0.10
    Activations Density 0.006%

    No Known Activations