© 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. 7-RESID-POST-AA
    11. 1493
    Prev
    Next
    INDEX
    Explanations

    LED screens/displays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    虽
    -0.08
    束
    -0.08
     interrupts
    -0.08
     বাধ
    -0.08
     অন্ত
    -0.07
     filings
    -0.07
    robat
    -0.07
    健
    -0.07
     Zuge
    -0.07
     prot
    -0.07
    POSITIVE LOGITS
     colo
    0.08
     Pase
    0.08
     haunted
    0.07
    �
    0.07
    �
    0.07
     rə
    0.07
     разреш
    0.07
    Magic
    0.07
    expr
    0.07
    mins
    0.07
    Activations Density 0.005%

    No Known Activations