© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    play

    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
     لاز
    -0.08
     Fang
    -0.08
     silicon
    -0.07
     SAR
    -0.07
     Jug
    -0.07
    佛
    -0.07
     oll
    -0.07
    刺
    -0.07
     Fiat
    -0.07
     visas
    -0.07
    POSITIVE LOGITS
     நடைபெ
    0.09
     நடந்த
    0.08
    קרה
    0.08
     ನಡೆದ
    0.08
    (Note
    0.08
     направ
    0.08
    яма
    0.08
     diesmal
    0.08
     நடைபெற்ற
    0.08
     ನಡೆಯ
    0.08
    Activations Density 0.004%

    No Known Activations