© 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. 102875
    Prev
    Next
    INDEX
    Explanations

    School/education context

    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
    ’eo
    -0.10
    าคาร่
    -0.10
    -ს
    -0.10
    ლი
    -0.09
    דורך
    -0.09
    าคาร่า
    -0.09
    დენ
    -0.09
    ლა
    -0.09
    -ზე
    -0.09
    ײ
    -0.09
    POSITIVE LOGITS
     другой
    0.08
     estando
    0.08
     অন্য
    0.08
    435
    0.07
     sauran
    0.07
    Bass
    0.07
     Друг
    0.07
     другого
    0.07
     полный
    0.07
    _Left
    0.07
    Activations Density 0.000%

    No Known Activations