© 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. 44638
    Prev
    Next
    INDEX
    Explanations

    chaos

    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
     oven
    -0.08
     Literacy
    -0.07
    費
    -0.07
    -learning
    -0.07
     literacy
    -0.07
    Foods
    -0.07
    ibi
    -0.07
     Hok
    -0.07
     potato
    -0.07
     promis
    -0.07
    POSITIVE LOGITS
     surreal
    0.10
     futuristic
    0.09
    战
    0.09
    _Render
    0.09
     casualties
    0.09
     രംഗ
    0.09
     частей
    0.09
     turmoil
    0.09
     вещей
    0.09
     драм
    0.09
    Activations Density 0.006%

    No Known Activations