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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31619
    Prev
    Next
    INDEX
    Explanations

    cross

    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
     NEWS
    -0.11
    다는
    -0.09
     Eating
    -0.09
    annik
    -0.09
    /md
    -0.09
     الطعام
    -0.08
    bets
    -0.08
     चाहिए
    -0.08
     Falle
    -0.08
     станов
    -0.08
    POSITIVE LOGITS
    -tier
    0.08
    -disciplinary
    0.08
     batt
    0.08
     effort
    0.08
     behavioral
    0.08
    ‑
    0.08
    -dimensional
    0.08
     mission
    0.08
    -party
    0.07
    ৈ
    0.07
    Activations Density 0.033%

    No Known Activations