© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    着

    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
     dedic
    -0.08
     Catal
    -0.08
     dí
    -0.08
    _cat
    -0.07
    -0.07
    edd
    -0.07
     curiosity
    -0.07
    ذك
    -0.07
    دى
    -0.07
     Catedral
    -0.07
    POSITIVE LOGITS
     sandwich
    0.09
     fick
    0.08
     Ort
    0.08
     Sandwich
    0.08
     -↵↵
    0.07
     hun
    0.07
    Brief
    0.07
     Vivian
    0.07
     alk
    0.07
     strapped
    0.07
    Activations Density 0.000%
    No Known Activations