© 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. 1348
    Prev
    Next
    INDEX
    Explanations

    Electrolysis

    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
    ><?=$
    -0.08
     能
    -0.08
    ROY
    -0.08
    天气
    -0.07
    细
    -0.07
    ္
    -0.07
    Nl
    -0.07
    独
    -0.07
     Sophia
    -0.07
    评
    -0.07
    POSITIVE LOGITS
     البل
    0.08
     aluminum
    0.08
     viz
    0.08
     deform
    0.08
     coloration
    0.08
     Radeon
    0.08
     Vulner
    0.08
     exfol
    0.08
     corrosion
    0.07
     lám
    0.07
    Activations Density 0.001%

    No Known Activations