© 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. 51420
    Prev
    Next
    INDEX
    Explanations

    ext

    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
    iban
    -0.09
     Quadrat
    -0.08
    azol
    -0.08
     decentralized
    -0.08
     tres
    -0.08
     Verkehr
    -0.08
    oth
    -0.08
    Az
    -0.07
     фас
    -0.07
     Az
    -0.07
    POSITIVE LOGITS
    iende
    0.11
    iénd
    0.10
    iência
    0.08
     popped
    0.08
    ienda
    0.08
    inción
    0.08
    i
    0.08
    æld
    0.08
    .ease
    0.08
     đặc
    0.08
    Activations Density 0.000%

    No Known Activations