© 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. 15-RESID-POST-AA
    11. 16328
    Prev
    Next
    INDEX
    Explanations

    artistic or cultural works

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amagitan
    -0.09
    abhairt
    -0.08
    umme
    -0.08
     +↵//
    -0.08
    иха
    -0.08
    ობას
    -0.08
    obozi
    -0.08
    ishini
    -0.08
    ე
    -0.08
    ายน
    -0.08
    POSITIVE LOGITS
     dédi
    0.09
     dedicated
    0.09
     attempts
    0.08
     devoted
    0.08
     titled
    0.08
     countless
    0.08
     variations
    0.07
    KK
    0.07
     various
    0.07
    .destroy
    0.07
    Activations Density 0.059%

    No Known Activations