© 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. 6679
    Prev
    Next
    INDEX
    Explanations

    мат

    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
     fuit
    -0.08
    ате
    -0.08
     Nd
    -0.08
    ड़
    -0.08
     Hr
    -0.08
     Md
    -0.08
    ante
    -0.07
     rád
    -0.07
    ddd
    -0.07
    аро
    -0.07
    POSITIVE LOGITS
    jó
    0.08
    AG
    0.08
     ಮಾ�
    0.08
     ਸੋ
    0.08
    ерин
    0.08
    -piece
    0.08
     peça
    0.08
     verdict
    0.08
     완
    0.07
    GT
    0.07
    Activations Density 0.000%

    No Known Activations