© 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. 3-RESID-POST-AA
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    ，以及

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    زه
    -0.07
     giờ
    -0.07
     bí
    -0.07
    hua
    -0.07
     الز
    -0.07
    .Glide
    -0.07
     ط
    -0.07
     mengg
    -0.07
    心水
    -0.07
    ยู
    -0.07
    POSITIVE LOGITS
     hypot
    0.08
     reciproc
    0.07
     ergo
    0.07
     sedent
    0.07
    没
    0.07
     hypotheses
    0.07
     trump
    0.07
     neg
    0.07
    &,
    0.07
     deles
    0.07
    Activations Density 0.000%

    No Known Activations