© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    会

    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
     cert
    -0.07
    ty
    -0.07
     emoji
    -0.07
    -e
    -0.07
     case
    -0.07
     far
    -0.07
     العلوم
    -0.07
     bus
    -0.07
    .jquery
    -0.07
     lok
    -0.07
    POSITIVE LOGITS
     Deco
    0.09
    णा
    0.08
    /software
    0.08
     Metall
    0.08
     deco
    0.08
     lineage
    0.08
     dẫn
    0.08
     engra
    0.08
     rehe
    0.07
     nevertheless
    0.07
    Activations Density 0.000%

    No Known Activations