© 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. 45608
    Prev
    Next
    INDEX
    Explanations

    skills/mastery

    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
    unnies
    -0.08
    uling
    -0.08
     donker
    -0.07
     AB
    -0.07
    uity
    -0.07
    /simple
    -0.07
     действие
    -0.07
     muffins
    -0.07
     कहना
    -0.07
     stated
    -0.07
    POSITIVE LOGITS
     firsthand
    0.13
     invaluable
    0.12
     valuable
    0.10
     lernen
    0.09
    .detach
    0.08
     Techniques
    0.08
    Kafka
    0.08
     deepen
    0.08
     Bloomberg
    0.08
     techniques
    0.08
    Activations Density 0.034%

    No Known Activations