© 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. 6278
    Prev
    Next
    INDEX
    Explanations

    Arabic, moderation

    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
    447
    -0.07
    META
    -0.07
    stdlib
    -0.07
     tid
    -0.07
     odpr
    -0.07
     gu
    -0.07
     total
    -0.07
     mushroom
    -0.07
    _li
    -0.07
     vocational
    -0.07
    POSITIVE LOGITS
    دل
    0.10
     moderation
    0.09
     moderated
    0.09
    واب
    0.08
    Throttle
    0.08
    قول
    0.08
    �
    0.08
     subdued
    0.08
    不过
    0.08
     douceur
    0.08
    Activations Density 0.001%

    No Known Activations