© 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. 99283
    Prev
    Next
    INDEX
    Explanations

    Ruby ActiveRecord models

    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
    azure
    -0.08
    gv
    -0.08
     powers
    -0.08
    Power
    -0.08
    %e
    -0.08
    आई
    -0.07
     power
    -0.07
     Humph
    -0.07
     Iber
    -0.07
    sett
    -0.07
    POSITIVE LOGITS
     تعلیم
    0.08
     enga
    0.08
     apropi
    0.08
     ترب
    0.07
     обработ
    0.07
     برید
    0.07
     коллед
    0.07
     tenido
    0.07
     Initialized
    0.07
     ")[
    0.07
    Activations Density 0.001%

    No Known Activations