© 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. 102806
    Prev
    Next
    INDEX
    Explanations

    HTML "bg" or "navbar"

    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
     छोट
    -0.09
     tighter
    -0.09
     tighten
    -0.09
    #+#+
    -0.09
     छोटे
    -0.09
     صغيرة
    -0.09
     nhỏ
    -0.09
     �
    -0.09
     קטן
    -0.09
     Tight
    -0.09
    POSITIVE LOGITS
     profound
    0.09
    iali
    0.08
    (gray
    0.07
     profunda
    0.07
    844
    0.07
    707
    0.07
    943
    0.07
     ആരോഗ്യ
    0.07
    .gray
    0.07
    636
    0.07
    Activations Density 0.000%

    No Known Activations