Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11594
    Prev
    Next
    INDEX
    Explanations

    guitar

    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
     ಎಂದು
    -0.08
    তম
    -0.08
     kitu
    -0.07
     Serg
    -0.07
    Elementary
    -0.07
     technically
    -0.07
    arries
    -0.07
    /XMLSchema
    -0.07
    tk
    -0.07
     inaad
    -0.07
    POSITIVE LOGITS
     밝
    0.08
    .gradient
    0.08
     चम
    0.08
     sail
    0.08
     okoli
    0.07
    okra
    0.07
    镜
    0.07
    опол
    0.07
     brighten
    0.07
    荒
    0.07
    Activations Density 0.008%

    No Known Activations