© 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. 49253
    Prev
    Next
    INDEX
    Explanations

    Abstract concepts

    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
     approach
    -0.13
     dataset
    -0.12
     subset
    -0.12
     environment
    -0.11
     relationship
    -0.11
    omgeving
    -0.11
     thing
    -0.11
     timeline
    -0.11
     situation
    -0.11
     regimen
    -0.11
    POSITIVE LOGITS
     territory
    0.15
     lore
    0.14
     fame
    0.13
     footage
    0.13
     legislation
    0.13
     technology
    0.13
     imagery
    0.13
     folklore
    0.12
     greatness
    0.12
     cuisine
    0.12
    Activations Density 0.438%

    No Known Activations