© 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. 3-RESID-POST-AA
    11. 13216
    Prev
    Next
    INDEX
    Explanations

    Camp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cooling
    -0.08
     cooling
    -0.08
     anex
    -0.07
     aero
    -0.07
     Aero
    -0.07
     habitu
    -0.07
     phe
    -0.07
     Els
    -0.07
     Hele
    -0.07
     Ary
    -0.07
    POSITIVE LOGITS
    DB
    0.08
     compromise
    0.07
    cka
    0.07
    чной
    0.07
     interval
    0.07
    oids
    0.07
     roster
    0.07
    Reduce
    0.07
     Moscow
    0.07
     rhetoric
    0.07
    Activations Density 0.007%

    No Known Activations