© 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. 11-RESID-POST-AA
    11. 639
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
    ，截至
    -0.08
     спорта
    -0.08
    ṛ
    -0.08
    affe
    -0.08
    ім
    -0.07
     עצמ
    -0.07
     bagi
    -0.07
     האתר
    -0.07
     состоянии
    -0.07
    ucken
    -0.07
    POSITIVE LOGITS
     expect
    0.09
    Expect
    0.08
    urio
    0.08
    强
    0.08
     reagent
    0.08
    QE
    0.08
     coma
    0.07
    produ
    0.07
    sie
    0.07
     cartoons
    0.07
    Activations Density 0.007%

    No Known Activations