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. 88065
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     alarms
    -0.08
     Bình
    -0.07
     Graves
    -0.07
    >()↵↵
    -0.07
     Catholic
    -0.07
     Nesse
    -0.07
    Encontr
    -0.07
     Cove
    -0.07
     seaside
    -0.07
     blogue
    -0.07
    POSITIVE LOGITS
     языка
    0.09
     пола
    0.08
     язык
    0.08
     доступны
    0.08
     wis
    0.08
    mw
    0.08
     naha
    0.08
    endidikan
    0.07
     специалисты
    0.07
     кто
    0.07
    Activations Density 0.086%

    No Known Activations