© 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. 50965
    Prev
    Next
    INDEX
    Explanations

    Random

    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
     Norske
    -0.08
    ுள்
    -0.08
    nelly
    -0.08
     Nen
    -0.08
     unes
    -0.07
     بهذا
    -0.07
     toppings
    -0.07
    .Columns
    -0.07
    voc
    -0.07
     Flores
    -0.07
    POSITIVE LOGITS
    Er
    0.10
    Choice
    0.10
     Flip
    0.09
     Er
    0.09
     flip
    0.09
    _flip
    0.09
     Choice
    0.09
    Flip
    0.08
     choice
    0.08
     ジ
    0.08
    Activations Density 0.000%

    No Known Activations