© 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. 12734
    Prev
    Next
    INDEX
    Explanations

    型

    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
    iges
    -0.08
     भाष
    -0.08
    wab
    -0.07
    COMM
    -0.07
    tribut
    -0.07
     कानून
    -0.07
     প্রতিষ্ঠ
    -0.07
    Gob
    -0.07
     Serif
    -0.07
     glaring
    -0.07
    POSITIVE LOGITS
     nasceu
    0.07
    透
    0.07
     unbeaten
    0.07
    透明
    0.07
    ೂ
    0.07
     konsep
    0.07
    _ci
    0.07
     zieht
    0.07
     formal
    0.07
     ICU
    0.07
    Activations Density 0.001%

    No Known Activations