© 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. 50845
    Prev
    Next
    INDEX
    Explanations

    San

    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
     üzere
    -0.09
    исиз
    -0.09
    <LM
    -0.08
    ыза
    -0.08
    ურდ
    -0.08
     anlam
    -0.08
     tengan
    -0.08
     бөт
    -0.07
     anmeld
    -0.07
     LDS
    -0.07
    POSITIVE LOGITS
    ırım
    0.10
    Disk
    0.09
    hed
    0.08
    atana
    0.08
    born
    0.08
    asar
    0.08
    tr
    0.08
    jab
    0.08
    laap
    0.08
    rey
    0.08
    Activations Density 0.005%

    No Known Activations