© 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. 51676
    Prev
    Next
    INDEX
    Explanations

    unrecognized token

    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
     g
    -0.11
    ounded
    -0.09
    ,g
    -0.08
     plas
    -0.08
     gra
    -0.08
     nagh
    -0.08
    .chrom
    -0.08
    গ্ৰ
    -0.08
     bob
    -0.08
    'g
    -0.08
    POSITIVE LOGITS
    Prefix
    0.09
    PREFIX
    0.09
     PREFIX
    0.09
    -prefix
    0.08
    Port
    0.08
    Prototype
    0.08
    Actor
    0.08
     Prefix
    0.07
    prefix
    0.07
     Frances
    0.07
    Activations Density 0.000%

    No Known Activations