© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48667
    Prev
    Next
    INDEX
    Explanations

    simple games

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trio
    -0.08
     COO
    -0.08
    BBW
    -0.08
     couture
    -0.08
     kompani
    -0.08
    ає
    -0.07
     exchanged
    -0.07
     compétition
    -0.07
     competitor
    -0.07
    -suite
    -0.07
    POSITIVE LOGITS
     Snake
    0.16
     Rock
    0.16
     Hang
    0.15
     Tic
    0.14
    Rock
    0.14
    Hang
    0.14
     Pong
    0.13
     hang
    0.13
     tic
    0.13
     rock
    0.13
    Activations Density 0.012%

    No Known Activations