© 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. 51332
    Prev
    Next
    INDEX
    Explanations

    pers

    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
    ાવે
    -0.07
     val
    -0.07
    Through
    -0.07
     solitary
    -0.07
    Ops
    -0.07
     cher
    -0.07
     શુ
    -0.07
    .assert
    -0.07
     lept
    -0.07
    ાવ
    -0.07
    POSITIVE LOGITS
    iste
    0.09
     historier
    0.09
     verble
    0.09
    isten
    0.09
     Dom
    0.08
    tria
    0.08
    istente
    0.08
    istency
    0.08
     Senator
    0.08
    inesi
    0.08
    Activations Density 0.000%

    No Known Activations