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. 67889
    Prev
    Next
    INDEX
    Explanations

    math competition problems

    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
     ejecut
    -0.08
     ejecutar
    -0.08
     තිබ
    -0.07
     någon
    -0.07
     aln
    -0.07
    從
    -0.07
     τε
    -0.07
    _execute
    -0.07
     हव
    -0.07
    ني
    -0.07
    POSITIVE LOGITS
    孤
    0.09
    WV
    0.08
    departure
    0.08
     Alone
    0.08
    所在
    0.08
     depot
    0.08
     promoção
    0.08
     अके
    0.08
     Isolation
    0.08
    ones
    0.08
    Activations Density 0.069%

    No Known Activations