© 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. 23-RESID-POST-AA
    11. 97600
    Prev
    Next
    INDEX
    Explanations

    수

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dll
    -0.09
     마지막
    -0.09
     문화
    -0.08
     Viagra
    -0.08
     �
    -0.08
    bucks
    -0.08
     ফোন
    -0.08
    IGINAL
    -0.08
     brewed
    -0.08
    ษายน
    -0.08
    POSITIVE LOGITS
    ক্ষেপ
    0.09
    험
    0.09
    казы
    0.08
    ർന്ന
    0.08
    ક્ષ
    0.08
    확
    0.08
    (水
    0.08
    ಕ್ಷ
    0.08
    납
    0.08
    രംഭ
    0.08
    Activations Density 0.000%

    No Known Activations