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. 119533
    Prev
    Next
    INDEX
    Explanations

    ^

    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
     Eco
    -0.08
    Eco
    -0.08
     ठ
    -0.08
     orphan
    -0.08
     तुम
    -0.07
     Mentor
    -0.07
     ชั้น
    -0.07
     पुर
    -0.07
    _CHO
    -0.07
     journalist
    -0.07
    POSITIVE LOGITS
     kons
    0.09
     Hare
    0.08
     calculation
    0.08
     Musa
    0.08
     məhs
    0.08
     Hathaway
    0.08
     célè
    0.08
     aspirin
    0.08
     reúne
    0.08
     asin
    0.07
    Activations Density 0.034%

    No Known Activations