© 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. 64676
    Prev
    Next
    INDEX
    Explanations

    Commutative/associative properties

    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
     jp
    -0.08
    jack
    -0.08
    ko
    -0.08
     JP
    -0.08
     Cord
    -0.08
    ifo
    -0.07
    oger
    -0.07
     Sahib
    -0.07
     RAW
    -0.07
     fade
    -0.07
    POSITIVE LOGITS
     cis
    0.08
    0.08
     assent
    0.08
     applicable
    0.07
     devis
    0.07
     pell
    0.07
     virtue
    0.07
    AGN
    0.07
     Leib
    0.07
     menghasilkan
    0.07
    Activations Density 0.003%
    No Known Activations