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. 27480
    Prev
    Next
    INDEX
    Explanations

    Oceania

    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
    foil
    -0.07
     Hamilton
    -0.07
     tecido
    -0.07
     precio
    -0.07
    naan
    -0.07
    _material
    -0.07
     quos
    -0.07
    JD
    -0.07
    mater
    -0.07
    aby
    -0.07
    POSITIVE LOGITS
     pinga
    0.09
    汽
    0.08
     encompass
    0.08
    leet
    0.08
    /setup
    0.08
     Leap
    0.08
     shit
    0.08
    BERS
    0.08
     Murphy
    0.08
     Cyrus
    0.08
    Activations Density 0.005%

    No Known Activations