© 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. 3-RESID-POST-AA
    11. 12939
    Prev
    Next
    INDEX
    Explanations

    ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hike
    -0.08
     fún
    -0.08
     Gary
    -0.07
    าคา
    -0.07
     plea
    -0.07
     stř
    -0.07
     lá
    -0.07
    答
    -0.07
     affirmative
    -0.07
     FL
    -0.07
    POSITIVE LOGITS
     Dari
    0.08
    145
    0.08
     smell
    0.08
    enti
    0.07
     props
    0.07
    Painting
    0.07
     그림
    0.07
    kom
    0.07
     painting
    0.07
    ordinate
    0.07
    Activations Density 0.001%

    No Known Activations