© 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 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. 63405
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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
     prestation
    -0.09
     ordre
    -0.09
     reassurance
    -0.09
     ordem
    -0.08
     crest
    -0.08
    ಾತ್ರಿ
    -0.08
    ാത്ര
    -0.08
     hourly
    -0.08
     minder
    -0.08
     рецепт
    -0.08
    POSITIVE LOGITS
     leaking
    0.11
     leakage
    0.11
     Leakage
    0.11
     attaques
    0.11
     attacks
    0.11
     leaks
    0.11
     ആക്രമ
    0.10
     공격
    0.10
    攻击
    0.10
    Leak
    0.10
    Activations Density 0.006%

    No Known Activations