© 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. 108419
    Prev
    Next
    INDEX
    Explanations

    design software instructions

    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
     sogenannte
    -0.09
     фестив
    -0.09
     правило
    -0.08
     Maz
    -0.08
     Eing
    -0.08
    usega
    -0.08
     Иг
    -0.08
    ＝
    -0.08
     yaitu
    -0.08
     moons
    -0.08
    POSITIVE LOGITS
     ולה
    0.09
     efficiently
    0.08
    Couldn't
    0.08
     efficacement
    0.08
    不错
    0.08
    Ap
    0.08
     canal
    0.07
    漂亮
    0.07
    -ap
    0.07
     gemakkelijk
    0.07
    Activations Density 0.279%

    No Known Activations