© 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. 23-RESID-POST-AA
    11. 5845
    Prev
    Next
    INDEX
    Explanations

    MQTT publish

    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
     consortium
    -0.08
     scenery
    -0.08
     omnes
    -0.08
     thromb
    -0.08
     kanten
    -0.08
     panoramic
    -0.08
     Baltic
    -0.08
    ビュー
    -0.07
     Bihar
    -0.07
     Spart
    -0.07
    POSITIVE LOGITS
     Qo
    0.15
    retain
    0.14
     publish
    0.14
    .publish
    0.13
     qos
    0.13
    _publish
    0.13
    Qo
    0.13
    Publish
    0.12
     Publish
    0.12
    publish
    0.12
    Activations Density 0.002%

    No Known Activations