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. 104226
    Prev
    Next
    INDEX
    Explanations

    class

    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
     Wol
    -0.08
     inhal
    -0.08
     meester
    -0.08
    geteilt
    -0.08
     wol
    -0.07
     रोग
    -0.07
     जुट
    -0.07
    wol
    -0.07
     പങ്ക
    -0.07
     crushing
    -0.07
    POSITIVE LOGITS
     Mih
    0.08
     filha
    0.08
     Notices
    0.08
     fille
    0.08
    Mash
    0.07
     içinde
    0.07
     Grou
    0.07
     içerisinde
    0.07
     Notice
    0.07
     Sell
    0.07
    Activations Density 0.008%

    No Known Activations