© 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. 47790
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
     .*
    -0.09
     stuffed
    -0.08
     behold
    -0.08
     silly
    -0.08
    wag
    -0.08
     whipped
    -0.08
     hunts
    -0.08
     spun
    -0.08
     inmates
    -0.08
     swimmers
    -0.08
    POSITIVE LOGITS
     mathematical
    0.17
     limitations
    0.16
     challenges
    0.15
     improvements
    0.15
     shortcomings
    0.15
     computational
    0.15
     scalability
    0.15
     techniques
    0.14
     preprocessing
    0.14
     drawbacks
    0.14
    Activations Density 0.064%

    No Known Activations