© 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. 95894
    Prev
    Next
    INDEX
    Explanations

    Fractals

    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
     tranquil
    -0.09
     sécurité
    -0.09
     standby
    -0.08
     inconvenience
    -0.08
     cirurgia
    -0.08
     turvall
    -0.08
     surveyed
    -0.08
    upuesto
    -0.08
     anesthesia
    -0.08
     safety
    -0.08
    POSITIVE LOGITS
     fract
    0.18
    actal
    0.11
    fract
    0.11
    _recursive
    0.10
     embracing
    0.09
     recursively
    0.09
     infinite
    0.09
     daddy
    0.08
     embraces
    0.08
     coastline
    0.08
    Activations Density 0.006%

    No Known Activations