© 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. 50570
    Prev
    Next
    INDEX
    Explanations

    Mixed Chinese/Programming snippets

    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
    ītu
    -0.09
     iby
    -0.09
     tín
    -0.08
    Leb
    -0.08
     ఇండ
    -0.08
     Leb
    -0.08
    nden
    -0.08
    čkog
    -0.08
     hemm
    -0.08
     crushed
    -0.08
    POSITIVE LOGITS
    _train
    0.08
    ella
    0.07
     Training
    0.07
     training
    0.07
    ati
    0.07
    اف
    0.07
    Script
    0.07
    ##
    0.07
    aila
    0.07
    .ctx
    0.07
    Activations Density 0.002%

    No Known Activations