© 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. 7-RESID-POST-AA
    11. 872
    Prev
    Next
    INDEX
    Explanations

    Chinese and limited resource context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addons
    -0.08
     puder
    -0.07
     Jos
    -0.07
     addon
    -0.07
    ben
    -0.07
     blah
    -0.07
    blah
    -0.07
     bob
    -0.07
    porte
    -0.07
     bevel
    -0.07
    POSITIVE LOGITS
     scarce
    0.11
     rares
    0.10
     dime
    0.09
    وک
    0.08
     ವಿರ
    0.08
     scarcity
    0.08
     rar
    0.08
    �
    0.08
     ресурсов
    0.08
     dearly
    0.08
    Activations Density 0.024%

    No Known Activations