© 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. 91340
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
     Advantage
    -0.07
     advantage
    -0.07
     nich
    -0.07
     gradually
    -0.07
    iec
    -0.07
    -coming
    -0.07
     ಎದು
    -0.07
     finden
    -0.07
    uniya
    -0.07
     Ni
    -0.07
    POSITIVE LOGITS
    painting
    0.09
    othèque
    0.08
     discusión
    0.08
    返信
    0.08
     Olive
    0.08
    .Paint
    0.08
     pizz
    0.08
     dejó
    0.08
    “I
    0.08
    등
    0.08
    Activations Density 0.002%

    No Known Activations