© 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. 96881
    Prev
    Next
    INDEX
    Explanations

    receiving notifications/deliveries

    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
    	found
    -0.10
    	using
    -0.10
    exists
    -0.09
    using
    -0.09
     mengambil
    -0.09
     gebruikte
    -0.09
     vorhand
    -0.09
    'etiti
    -0.09
     reachable
    -0.09
     utilisant
    -0.09
    POSITIVE LOGITS
     удовольствие
    0.14
     notification
    0.13
     уведом
    0.13
     notifications
    0.13
     منك
    0.13
    通知
    0.13
    来自
    0.12
     подарок
    0.12
    _notification
    0.12
     �
    0.12
    Activations Density 0.145%

    No Known Activations