© 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. 102896
    Prev
    Next
    INDEX
    Explanations

    validation

    np_max-act-logits · gemini-2.0-flash

    The neuron detects tokens related to validation/verification (words about checking, validating, or verifying).

    oai_token-act-pair · gpt-5-miniTriggered by @forsubscription1
    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
    �ես
    -0.08
    არეობ
    -0.08
    �ე
    -0.08
     swes
    -0.08
    րանք
    -0.08
    ാളെ
    -0.08
    არეობს
    -0.08
    keleton
    -0.08
    ണി
    -0.08
    �ლი
    -0.08
    POSITIVE LOGITS
    idação
    0.18
    ating
    0.15
    验证
    0.14
    .validate
    0.14
    (validate
    0.14
     Validate
    0.14
    alid
    0.13
    ates
    0.13
    Validate
    0.13
    validate
    0.13
    Activations Density 0.010%

    No Known Activations