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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102903
    Prev
    Next
    INDEX
    Explanations

    say relative pronoun

    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
     representing
    -0.15
     resembling
    -0.13
     containing
    -0.13
     encompassing
    -0.13
     contendo
    -0.13
     involving
    -0.12
     comprising
    -0.12
     pertaining
    -0.12
     consisting
    -0.12
     relating
    -0.12
    POSITIVE LOGITS
     that
    0.23
     которые
    0.19
     που
    0.19
     التي
    0.19
     که
    0.18
     yang
    0.18
    that
    0.17
    ที่
    0.17
     That
    0.16
     who
    0.16
    Activations Density 0.092%

    No Known Activations