© 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. 95719
    Prev
    Next
    INDEX
    Explanations

    sorting algorithms

    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
    _vocab
    -0.08
    立即
    -0.07
     בת
    -0.07
    膜
    -0.07
    uco
    -0.07
    nah
    -0.07
     nhận
    -0.07
    -0.07
     beauty
    -0.07
    .contacts
    -0.07
    POSITIVE LOGITS
    Fallback
    0.10
    optimized
    0.10
    fallback
    0.10
     optimized
    0.09
     Abram
    0.09
    stab
    0.09
    -tested
    0.09
     Cuomo
    0.08
     Complexity
    0.08
    Kort
    0.08
    Activations Density 0.002%
    No Known Activations