© 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. 95803
    Prev
    Next
    INDEX
    Explanations

    Art descriptions/metadata

    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
     suma
    -0.07
    ddit
    -0.07
     arise
    -0.07
    ర్స్
    -0.07
    allax
    -0.07
     lazer
    -0.07
     drained
    -0.07
     prej
    -0.07
     underlying
    -0.07
     luke
    -0.07
    POSITIVE LOGITS
    خط
    0.08
    ember
    0.07
    �
    0.07
     Invent
    0.07
    EMBER
    0.07
    其它
    0.07
    ểu
    0.07
     پہ
    0.07
    ته
    0.07
    یر
    0.07
    Activations Density 0.006%

    No Known Activations