© 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. 129567
    Prev
    Next
    INDEX
    Explanations

    atomic operations

    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
     objectively
    -0.08
     teammates
    -0.08
    ின்
    -0.08
     faint
    -0.08
     mellow
    -0.07
    _dead
    -0.07
    店
    -0.07
     ٿا
    -0.07
     mites
    -0.07
     invité
    -0.07
    POSITIVE LOGITS
     erfolgen
    0.09
     किए
    0.09
     операций
    0.09
     операции
    0.09
     dilakukan
    0.08
     durchgeführt
    0.08
     takeover
    0.08
    asper
    0.07
     Aktual
    0.07
     durchführen
    0.07
    Activations Density 0.002%

    No Known Activations