© 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. 50936
    Prev
    Next
    INDEX
    Explanations

    pre

    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
    ają
    -0.08
     arrested
    -0.07
    olla
    -0.07
    Pas
    -0.07
     Pas
    -0.07
     vraag
    -0.07
    ساء
    -0.07
     staring
    -0.07
     foundation
    -0.07
     Centrale
    -0.07
    POSITIVE LOGITS
    号
    0.10
    號
    0.10
    pozn
    0.09
    968
    0.08
    ичь
    0.08
    lygy
    0.08
    ure
    0.08
    ্যাক
    0.08
    .Cookie
    0.07
    prič
    0.07
    Activations Density 0.000%

    No Known Activations