© 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. 129305
    Prev
    Next
    INDEX
    Explanations

    Russian government decrees

    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
     Spy
    -0.09
     Diplom
    -0.09
     diplomacy
    -0.08
     Tweet
    -0.08
     Tarot
    -0.08
     Macintosh
    -0.08
     chir
    -0.08
     exactamente
    -0.08
     Trojan
    -0.08
     обнаруж
    -0.08
    POSITIVE LOGITS
    acal
    0.08
     finer
    0.08
    Additional
    0.07
    Supporting
    0.07
    ätze
    0.07
     detailing
    0.07
    Level
    0.07
    Calibration
    0.07
     fines
    0.07
    serie
    0.07
    Activations Density 0.009%

    No Known Activations