© 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. 13220
    Prev
    Next
    INDEX
    Explanations

    sense

    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
     증
    -0.10
     residencia
    -0.08
     kron
    -0.08
     Holm
    -0.08
    /sw
    -0.07
     קור
    -0.07
     Presid
    -0.07
     প্রতিব
    -0.07
     jal
    -0.07
     ACS
    -0.07
    POSITIVE LOGITS
    zeit
    0.08
     önem
    0.08
    ipes
    0.07
     ofrecer
    0.07
     Eugene
    0.07
    play
    0.07
    ospel
    0.07
     Loja
    0.07
     vanity
    0.07
    азара
    0.07
    Activations Density 0.002%

    No Known Activations