© 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. 47843
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     ACL
    -0.07
     needles
    -0.07
     ಪ್ರಕ
    -0.07
     Handmade
    -0.07
     richness
    -0.07
     richer
    -0.07
     제조
    -0.07
    ocas
    -0.07
    越来越
    -0.07
     רח
    -0.07
    POSITIVE LOGITS
     Chavez
    0.09
     Relationships
    0.09
     VALUES
    0.09
     gha
    0.08
     Chávez
    0.08
     sien
    0.08
     crore
    0.08
     Pablo
    0.08
    اؤ
    0.08
    Relationships
    0.08
    Activations Density 0.086%

    No Known Activations