© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 947
    Prev
    Next
    INDEX
    Explanations

    spam, dating, search terms

    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
     supra
    -0.08
     kine
    -0.08
     exce
    -0.08
     Intervention
    -0.08
     Optional
    -0.07
     restitution
    -0.07
     Runnable
    -0.07
    毁
    -0.07
     rhe
    -0.07
     Humanities
    -0.07
    POSITIVE LOGITS
    203
    0.10
    888
    0.09
     ਕੁ
    0.08
     รวม
    0.08
    FAQs
    0.08
    _GET
    0.08
    _find
    0.08
    �
    0.08
     southwest
    0.08
    797
    0.08
    Activations Density 0.144%

    No Known Activations