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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78281
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    iyet
    -0.08
     unusually
    -0.08
    Keywords
    -0.08
     Keywords
    -0.08
     diye
    -0.08
     mà
    -0.07
     ăn
    -0.07
     Du
    -0.07
    ccin
    -0.07
    חה
    -0.07
    POSITIVE LOGITS
    不知道
    0.12
     জানতে
    0.10
     తెలియ
    0.10
     தெரிய
    0.09
     desconoc
    0.09
     తెలుస
    0.09
     unknown
    0.09
    /no
    0.09
     clueless
    0.08
     shuffle
    0.08
    Activations Density 0.021%

    No Known Activations