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. 49345
    Prev
    Next
    INDEX
    Explanations

    data oversampling

    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
    (moment
    -0.09
     tois
    -0.08
    immungen
    -0.08
     reunited
    -0.08
    arded
    -0.08
     conven
    -0.08
    جد
    -0.08
    اید
    -0.08
     مادة
    -0.08
    ظ
    -0.08
    POSITIVE LOGITS
     artır
    0.09
     handmade
    0.08
     augment
    0.08
     smarter
    0.08
     umjet
    0.08
     entourage
    0.08
     sklearn
    0.08
     resh
    0.08
     handcrafted
    0.07
     augmenter
    0.07
    Activations Density 0.001%

    No Known Activations