© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21785
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rhône
    -0.08
     إيران
    -0.08
     সূত্র
    -0.08
     الأسد
    -0.08
     न्याय
    -0.08
     وړ
    -0.08
    .EMPTY
    -0.08
    ساس
    -0.08
     Draw
    -0.08
     Dortmund
    -0.07
    POSITIVE LOGITS
    byte
    0.17
    memory
    0.16
     byte
    0.16
    (byte
    0.15
     memory
    0.15
    	byte
    0.14
    _byte
    0.14
    .memory
    0.13
    (memory
    0.12
    .byte
    0.12
    Activations Density 0.001%

    No Known Activations