© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    as

    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
     they'll
    -0.08
     Paradise
    -0.07
     Fulton
    -0.07
     probate
    -0.07
     Prague
    -0.07
     pratic
    -0.07
     Lyon
    -0.07
    /:
    -0.07
     currents
    -0.07
     SSA
    -0.07
    POSITIVE LOGITS
     cork
    0.08
    cussion
    0.08
     kord
    0.07
    ception
    0.07
     cerebro
    0.07
     wig
    0.07
     usein
    0.07
     hated
    0.07
     wicket
    0.07
    shima
    0.07
    Activations Density 0.000%

    No Known Activations