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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129616
    Prev
    Next
    INDEX
    Explanations

    shuffle

    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
    phan
    -0.08
     bł
    -0.08
    avelength
    -0.08
     підтрим
    -0.08
    -esteem
    -0.07
     metabolism
    -0.07
     मुद्द
    -0.07
    벤
    -0.07
    支
    -0.07
     pride
    -0.07
    POSITIVE LOGITS
    .shuffle
    0.15
     shuffled
    0.15
     Shuffle
    0.13
     shuffle
    0.13
    Shuffle
    0.12
    /random
    0.12
    shuffle
    0.11
    _shuffle
    0.11
     randomized
    0.11
     randomness
    0.10
    Activations Density 0.009%

    No Known Activations