Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65669
    Prev
    Next
    INDEX
    Explanations

    exist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.08
     bille
    -0.08
    组
    -0.08
    757
    -0.08
    PX
    -0.08
    (bot
    -0.08
    -sch
    -0.07
     engulf
    -0.07
     offenses
    -0.07
    ển
    -0.07
    POSITIVE LOGITS
     Nun
    0.08
     Pon
    0.08
    ので
    0.07
     wen
    0.07
     UV
    0.07
     Bef
    0.07
     fo
    0.07
    จริง
    0.07
     Vlad
    0.07
     ike
    0.07
    Activations Density 0.030%

    No Known Activations