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. 3-RESID-POST-AA
    6. 12336
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vent
    -0.08
    idel
    -0.08
    birthday
    -0.08
     Fey
    -0.08
    hut
    -0.08
    voucher
    -0.08
     vent
    -0.07
     hoodie
    -0.07
    newsletter
    -0.07
    erp
    -0.07
    POSITIVE LOGITS
    ,—
    0.08
     chiefly
    0.08
     useless
    0.08
     cá
    0.07
    Persons
    0.07
     APPLICATION
    0.07
     सहयोग
    0.07
     mira
    0.07
     radians
    0.07
     mammals
    0.07
    Activations Density 0.020%

    No Known Activations