© 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. 3-RESID-POST-AA
    11. 2739
    Prev
    Next
    INDEX
    Explanations

    lost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hug
    -0.08
     Fais
    -0.08
     revamped
    -0.08
     Epstein
    -0.07
     saf
    -0.07
     Tate
    -0.07
     κά
    -0.07
     Washington
    -0.07
     patente
    -0.07
     parcours
    -0.07
    POSITIVE LOGITS
    atten
    0.09
     아니라
    0.08
    务
    0.07
     spontaneous
    0.07
     overshadow
    0.07
     spontaneously
    0.07
     아닌
    0.07
     ross
    0.07
     crossed
    0.07
     مناف
    0.07
    Activations Density 0.013%

    No Known Activations