© 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. 103131
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     Atmosphäre
    -0.08
     обладает
    -0.08
     бірақ
    -0.08
    版权
    -0.07
     inning
    -0.07
    名無し
    -0.07
     victime
    -0.07
     embarrassing
    -0.07
     бывает
    -0.07
     تعتبر
    -0.07
    POSITIVE LOGITS
     distances
    0.19
     distance
    0.18
    distance
    0.17
    _distance
    0.17
    Distance
    0.17
     Distance
    0.17
    .Distance
    0.16
    距离
    0.16
     दूरी
    0.16
     distancia
    0.15
    Activations Density 0.035%

    No Known Activations