© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108189
    Prev
    Next
    INDEX
    Explanations

    up

    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
     Types
    -0.07
     मंगल
    -0.07
    ambili
    -0.07
     ongoing
    -0.07
     truncate
    -0.07
    ең
    -0.07
     modular
    -0.07
     stagger
    -0.07
     Joe
    -0.07
     singular
    -0.07
    POSITIVE LOGITS
    up
    0.08
    ipal
    0.08
     comfortably
    0.08
    /out
    0.08
    reference
    0.07
    down
    0.07
    drive
    0.07
    Reference
    0.07
    Convertible
    0.07
     compet
    0.07
    Activations Density 0.001%

    No Known Activations