© 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. 103159
    Prev
    Next
    INDEX
    Explanations

    Also

    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
    .↵
    -0.11
    -focused
    -0.11
    -era
    -0.11
    (...)↵
    -0.10
    ."↵
    -0.10
    **↵
    -0.10
    -est
    -0.10
    ‑
    -0.10
    ()↵
    -0.10
    -themed
    -0.10
    POSITIVE LOGITS
     note
    0.25
     also
    0.18
     need
    0.18
     importantly
    0.17
     Note
    0.17
     the
    0.16
     since
    0.16
     it's
    0.16
     noting
    0.16
     remember
    0.16
    Activations Density 0.048%

    No Known Activations