© 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. 48058
    Prev
    Next
    INDEX
    Explanations

    code/equations/quotes

    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
     ორგან
    -0.08
     quý
    -0.08
     დან
    -0.08
    trs
    -0.08
     เครดิตฟรี
    -0.08
     เครดิต
    -0.08
     memorandum
    -0.08
     विकास
    -0.08
     कै
    -0.08
    เด็ด
    -0.08
    POSITIVE LOGITS
     vision
    0.08
     nao
    0.07
     demande
    0.07
    vox
    0.07
     Meetup
    0.07
    Vision
    0.07
     schre
    0.07
    .gz
    0.07
     Front
    0.07
     Schritt
    0.07
    Activations Density 0.001%

    No Known Activations