© 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. 95204
    Prev
    Next
    INDEX
    Explanations

    Moore

    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
     powder
    -0.09
     passwd
    -0.08
     DWORD
    -0.08
     gud
    -0.07
     Powder
    -0.07
    (group
    -0.07
    .gray
    -0.07
     оста
    -0.07
     અવ
    -0.07
     forth
    -0.07
    POSITIVE LOGITS
    Animals
    0.09
     Animals
    0.09
     الحيوانات
    0.08
     nautical
    0.08
     Tiere
    0.08
     perros
    0.08
     mascotas
    0.08
    ें
    0.08
     animals
    0.08
    नेपाल
    0.07
    Activations Density 0.001%

    No Known Activations