© 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. 47494
    Prev
    Next
    INDEX
    Explanations

    Lab procedures

    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
    quisite
    -0.08
    情
    -0.07
     rampant
    -0.07
     устран
    -0.07
     rife
    -0.07
     испыты
    -0.07
     livres
    -0.07
     complet
    -0.07
     Será
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     ungg
    0.08
    mester
    0.08
    dump
    0.08
     mixtures
    0.08
     schwarz
    0.08
     antiguos
    0.08
    Dump
    0.08
    Ct
    0.08
     mixture
    0.08
    itekt
    0.08
    Activations Density 0.002%

    No Known Activations