© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47909
    Prev
    Next
    INDEX
    Explanations

    math/CS terms

    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
    A
    -0.09
    a
    -0.08
     A
    -0.08
     ajo
    -0.08
     aqua
    -0.08
    dictionary
    -0.08
    Mar
    -0.07
    "M
    -0.07
     HIGH
    -0.07
    AVE
    -0.07
    POSITIVE LOGITS
    cte
    0.09
    enoside
    0.08
     એન
    0.08
    ynyt
    0.08
    yans
    0.08
    yni
    0.08
    ylim
    0.08
    yse
    0.08
    yac
    0.08
     crap
    0.08
    Activations Density 0.014%

    No Known Activations