© 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. 29277
    Prev
    Next
    INDEX
    Explanations

    Palindrome numbers

    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
     Sculpt
    -0.08
     sculpt
    -0.07
     باید
    -0.07
     cuidar
    -0.07
    Circular
    -0.07
    asio
    -0.07
    zył
    -0.07
     último
    -0.07
     inglés
    -0.07
    ició
    -0.07
    POSITIVE LOGITS
    等等
    0.09
    OSE
    0.08
    など
    0.08
    各种
    0.08
     οι
    0.08
     usw
    0.08
    以
    0.08
     też
    0.08
     itd
    0.07
    Choices
    0.07
    Activations Density 0.017%

    No Known Activations