© 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. 18984
    Prev
    Next
    INDEX
    Explanations

    say "half"

    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
     parmi
    -0.08
    zif
    -0.07
     требований
    -0.07
     numbered
    -0.07
     убеж
    -0.07
    ometers
    -0.07
     strategi
    -0.07
    OME
    -0.07
    Among
    -0.07
    кут
    -0.07
    POSITIVE LOGITS
     quarter
    0.13
     half
    0.13
     third
    0.12
     moitié
    0.12
     halves
    0.11
     thirds
    0.11
     半
    0.11
     derde
    0.11
     Hälfte
    0.11
     השני
    0.10
    Activations Density 0.008%

    No Known Activations