© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24909
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Savior
    -0.08
     anmelden
    -0.08
     connecté
    -0.07
     Calabria
    -0.07
     Insel
    -0.07
     dargestellt
    -0.07
     Convenience
    -0.07
    icient
    -0.07
     скач
    -0.07
     жер
    -0.07
    POSITIVE LOGITS
    色
    0.10
    �
    0.10
     scents
    0.09
     enthusiasm
    0.09
     उत्स
    0.09
     aromas
    0.09
     రంగ
    0.08
     നിറ
    0.08
     vibrations
    0.08
    epsilon
    0.08
    Activations Density 0.018%

    No Known Activations