© 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. 75880
    Prev
    Next
    INDEX
    Explanations

    Warnings

    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
     yıll
    -0.09
     другу
    -0.08
     strangely
    -0.08
     searches
    -0.08
    ethode
    -0.08
     пусть
    -0.07
     sø
    -0.07
    ennial
    -0.07
     நிர
    -0.07
     تقريب
    -0.07
    POSITIVE LOGITS
     pitfalls
    0.13
    注意
    0.12
     vigilant
    0.12
     vigilance
    0.12
     caution
    0.12
     साव
    0.12
     careful
    0.11
     осторож
    0.11
     注意
    0.11
     вним
    0.10
    Activations Density 0.042%

    No Known Activations