© 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. 23-RESID-POST-AA
    11. 6605
    Prev
    Next
    INDEX
    Explanations

    climate patterns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialties
    -0.09
     especializada
    -0.09
     UICollection
    -0.09
    Collection
    -0.08
    _dirs
    -0.08
     spécialistes
    -0.08
    _vector
    -0.08
     especializado
    -0.08
     consultancy
    -0.08
     specialist
    -0.08
    POSITIVE LOGITS
     blocking
    0.10
     La
    0.09
     Halloween
    0.09
    Halloween
    0.09
     El
    0.09
     Blocking
    0.09
     blocked
    0.09
     Madden
    0.09
     ANA
    0.08
     quasi
    0.08
    Activations Density 0.006%

    No Known Activations