© 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. 18649
    Prev
    Next
    INDEX
    Explanations

    say "with, via, using"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Based
    -0.10
    Based
    -0.09
    　在
    -0.09
     basé
    -0.08
    _based
    -0.08
    	include
    -0.08
     在
    -0.08
     basée
    -0.08
    Includes
    -0.08
    based
    -0.07
    POSITIVE LOGITS
    ด้วย
    0.12
     dening
    0.11
     توسط
    0.11
     suing
    0.10
     nganggo
    0.10
     باستخدام
    0.10
     بـ
    0.10
    โดย
    0.10
     через
    0.09
     with
    0.09
    Activations Density 0.059%

    No Known Activations