© 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. 1249
    Prev
    Next
    INDEX
    Explanations

    map

    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
     kiy
    -0.07
     recurse
    -0.07
     polishing
    -0.07
     Couple
    -0.07
     recursion
    -0.07
     хран
    -0.07
     rato
    -0.07
     mire
    -0.07
     있음
    -0.07
     ficha
    -0.07
    POSITIVE LOGITS
     NGOs
    0.09
     geography
    0.09
    面积
    0.09
     geographically
    0.09
     overlays
    0.08
     scientifically
    0.08
    .Country
    0.08
     Overlay
    0.08
    犯罪
    0.08
     continents
    0.08
    Activations Density 0.011%

    No Known Activations