© 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. 43573
    Prev
    Next
    INDEX
    Explanations

    non-English

    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
     experimented
    -0.08
    lections
    -0.08
     신고
    -0.08
     고민
    -0.08
    ecz
    -0.08
    nation
    -0.07
    aculture
    -0.07
     reais
    -0.07
     보여
    -0.07
     panoramic
    -0.07
    POSITIVE LOGITS
    ivt
    0.09
     ಕಾಂ
    0.08
     tia
    0.07
    ਆ
    0.07
     frå
    0.07
    霍
    0.07
    ‌ನ
    0.07
     卡
    0.07
    േസ
    0.07
     extracts
    0.07
    Activations Density 0.259%

    No Known Activations