© 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. 19-RESID-POST-AA
    11. 18759
    Prev
    Next
    INDEX
    Explanations

    say "ible"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дание
    -0.09
    дания
    -0.09
    atlar
    -0.09
    rachadh
    -0.08
    აზი
    -0.08
    что
    -0.08
    дани
    -0.08
    קום
    -0.08
    dən
    -0.08
    painting
    -0.08
    POSITIVE LOGITS
    ible
    0.21
    ibility
    0.19
    ibles
    0.13
    able
    0.12
    ibly
    0.12
    ibile
    0.11
    IBLE
    0.11
    ive
    0.11
    ibilities
    0.11
    ial
    0.10
    Activations Density 0.001%

    No Known Activations