© 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. 44482
    Prev
    Next
    INDEX
    Explanations

    margherita pizza

    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
     preparedness
    -0.08
    _oper
    -0.08
     winnen
    -0.08
    umped
    -0.08
     Vermont
    -0.08
     thoughtful
    -0.08
     scents
    -0.07
    rar
    -0.07
     proactively
    -0.07
     preorder
    -0.07
    POSITIVE LOGITS
     consisting
    0.09
    ιος
    0.08
     dalla
    0.08
     Paulista
    0.08
    Simple
    0.08
    0.08
     SAC
    0.07
    ಿಯೋ
    0.07
     consists
    0.07
     bure
    0.07
    Activations Density 0.002%
    No Known Activations