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. 74767
    Prev
    Next
    INDEX
    Explanations

    igen

    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
     foyer
    -0.10
    大厅
    -0.08
     dl
    -0.08
     chut
    -0.08
    لحة
    -0.08
     Butt
    -0.08
    นี้
    -0.08
    loo
    -0.08
     flea
    -0.07
     pies
    -0.07
    POSITIVE LOGITS
    medicine
    0.07
     enhancer
    0.07
    rosion
    0.07
    markers
    0.07
     gede
    0.07
    conf
    0.07
    Seg
    0.07
     Ond
    0.07
    019
    0.07
     methyl
    0.07
    Activations Density 0.002%

    No Known Activations