© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 95802
    Prev
    Next
    INDEX
    Explanations

    equity

    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
     Adhes
    -0.08
     vibr
    -0.08
    '↵↵↵
    -0.08
     निश्चित
    -0.08
     स्पष्ट
    -0.08
     काय
    -0.08
     الأش
    -0.08
     svojih
    -0.08
    шийся
    -0.08
    '+
    -0.07
    POSITIVE LOGITS
    Ei
    0.07
     Explorer
    0.07
     Dior
    0.07
    赞
    0.07
    handeling
    0.07
    enties
    0.07
     Merk
    0.07
    aup
    0.07
    .post
    0.07
     enquiries
    0.07
    Activations Density 0.002%

    No Known Activations