© 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. 44299
    Prev
    Next
    INDEX
    Explanations

    constructive

    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
     Execution
    -0.08
     Alberto
    -0.07
     echo
    -0.07
    īja
    -0.07
    ono
    -0.07
    uttering
    -0.07
    ceived
    -0.07
     vertellen
    -0.07
    .raw
    -0.07
    raw
    -0.07
    POSITIVE LOGITS
     respectful
    0.12
    尊
    0.11
     peacefully
    0.11
     preferably
    0.10
     respe
    0.10
     peaceful
    0.10
     calmly
    0.10
     constructive
    0.10
     gentle
    0.10
     rather
    0.09
    Activations Density 0.076%

    No Known Activations