© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69518
    Prev
    Next
    INDEX
    Explanations

    the

    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
     regels
    -0.08
     rules
    -0.08
     αυτού
    -0.07
     mortgage
    -0.07
     أح
    -0.07
    YN
    -0.07
    Mem
    -0.07
    待遇
    -0.07
     million
    -0.07
     mint
    -0.07
    POSITIVE LOGITS
    lying
    0.09
     расположен
    0.09
     связано
    0.09
     главный
    0.08
     Sahib
    0.08
     odpow
    0.08
     पुग
    0.08
    �
    0.08
     raíz
    0.08
     аэроп
    0.08
    Activations Density 0.040%

    No Known Activations