© 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. 51475
    Prev
    Next
    INDEX
    Explanations

    "to be" verb

    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
     pertaining
    -0.11
     with
    -0.09
     having
    -0.09
     counted
    -0.09
    ecution
    -0.08
    taken
    -0.08
     Served
    -0.08
     waited
    -0.08
     accounted
    -0.08
     ด้วย
    -0.08
    POSITIVE LOGITS
     designed
    0.11
     capaz
    0.11
     developed
    0.10
     meticulous
    0.10
     based
    0.10
     gebaseerd
    0.10
     la
    0.10
     redesigned
    0.10
     notorious
    0.09
    based
    0.09
    Activations Density 0.039%

    No Known Activations