© 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. 30162
    Prev
    Next
    INDEX
    Explanations

    total

    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
    Stamped
    -0.08
     exemplar
    -0.08
     Roads
    -0.08
     wearable
    -0.08
     sidewalks
    -0.08
     stamped
    -0.07
     road
    -0.07
    _stamp
    -0.07
    Stamp
    -0.07
     mf
    -0.07
    POSITIVE LOGITS
     القرآن
    0.08
     العقل
    0.08
     pregnancies
    0.08
    awasan
    0.08
     loin
    0.07
    ouver
    0.07
    moder
    0.07
    αν
    0.07
     Idol
    0.07
    reek
    0.07
    Activations Density 0.000%

    No Known Activations