© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108642
    Prev
    Next
    INDEX
    Explanations

    {

    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
    Sac
    -0.08
     Sacred
    -0.08
    ı
    -0.08
    Geo
    -0.08
     innocent
    -0.07
     grandeur
    -0.07
    कारी
    -0.07
    บาคาร่า
    -0.07
    Sug
    -0.07
    降
    -0.07
    POSITIVE LOGITS
     hinges
    0.08
     Orr
    0.08
    answer
    0.08
     willow
    0.08
     ਸਭ
    0.07
     lutter
    0.07
    SEMB
    0.07
     brass
    0.07
    well
    0.07
    curl
    0.07
    Activations Density 0.005%

    No Known Activations