© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110477
    Prev
    Next
    INDEX
    Explanations

    violence

    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
    Ali
    -0.09
     Alias
    -0.08
     Ordinary
    -0.08
    排列
    -0.08
     Aquarius
    -0.07
     Apostle
    -0.07
     Ali
    -0.07
     kuona
    -0.07
     Alibaba
    -0.07
     ali
    -0.07
    POSITIVE LOGITS
     unethical
    0.09
    উ
    0.09
     oppression
    0.09
     unlaw
    0.08
     незакон
    0.07
    536
    0.07
     wrongdoing
    0.07
    हे
    0.07
    য
    0.07
     disclosures
    0.07
    Activations Density 0.026%

    No Known Activations