© 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. 23-RESID-POST-AA
    11. 51780
    Prev
    Next
    INDEX
    Explanations

    202

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unda
    -0.08
    today
    -0.08
     rigu
    -0.07
    積
    -0.07
     academia
    -0.07
    芽
    -0.07
     faveur
    -0.07
     Irlanda
    -0.07
    וקים
    -0.07
     traditionally
    -0.07
    POSITIVE LOGITS
    ക്സ
    0.08
    348
    0.08
    %%%
    0.08
     hlay
    0.08
    gleich
    0.08
    ателю
    0.08
    cpy
    0.08
    ക്
    0.08
    ‍ക്ക്
    0.08
     تک
    0.08
    Activations Density 0.002%

    No Known Activations