© 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. 50445
    Prev
    Next
    INDEX
    Explanations

    say ending -aded/-aped

    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
     UPDATED
    -0.08
    OT
    -0.08
     defect
    -0.08
    CLICK
    -0.08
    UFACT
    -0.08
     নিশ্চ
    -0.08
    ip
    -0.08
    不要
    -0.08
    -ip
    -0.08
     CLICK
    -0.08
    POSITIVE LOGITS
    apes
    0.14
    aped
    0.13
    rink
    0.13
    allow
    0.12
    rine
    0.12
    ifting
    0.12
    run
    0.11
    aded
    0.10
    ading
    0.10
    apest
    0.09
    Activations Density 0.009%

    No Known Activations