© 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. 114039
    Prev
    Next
    INDEX
    Explanations

    her

    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
    的天天
    -0.09
     Campeonato
    -0.09
    무
    -0.08
    ետի
    -0.08
     Jangan
    -0.08
     beraten
    -0.08
     Histor
    -0.08
    .synthetic
    -0.08
    lüğ
    -0.08
     consta
    -0.08
    POSITIVE LOGITS
     צד
    0.08
    들
    0.07
     possibilidade
    0.07
     Brett
    0.07
    Combination
    0.07
    Passengers
    0.07
     circunst
    0.07
     exceptional
    0.07
     swap
    0.07
    (adj
    0.07
    Activations Density 0.000%

    No Known Activations