© 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. 44788
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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
    ៗ
    -0.09
     sanctions
    -0.08
     Would
    -0.08
     Cooler
    -0.07
     Cooling
    -0.07
    .netflix
    -0.07
     Viola
    -0.07
     Travels
    -0.07
     dynamique
    -0.07
     Sessions
    -0.07
    POSITIVE LOGITS
     hors
    0.08
    hod
    0.08
     pute
    0.08
     KU
    0.08
     \↵
    0.07
     XK
    0.07
     αν
    0.07
     proyek
    0.07
     rejoint
    0.07
    ANI
    0.07
    Activations Density 0.005%

    No Known Activations