© 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. 6429
    Prev
    Next
    INDEX
    Explanations

    different languages

    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
    	go
    -0.07
    横
    -0.07
    (go
    -0.07
     GO
    -0.07
     spu
    -0.07
     game
    -0.07
    ದಿ
    -0.07
     ni
    -0.07
     Ak
    -0.07
    GO
    -0.07
    POSITIVE LOGITS
    érés
    0.09
     табылады
    0.08
    শ্য
    0.08
    етел
    0.08
    �்க
    0.08
    lyn
    0.08
    .resolve
    0.08
    plies
    0.08
    uada
    0.08
    édia
    0.08
    Activations Density 0.009%

    No Known Activations