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. 8841
    Prev
    Next
    INDEX
    Explanations

    replace/`sed` command

    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
     cair
    -0.08
     monoxide
    -0.08
     domác
    -0.08
     nurt
    -0.08
     بك
    -0.08
    ,例如
    -0.08
    ُل
    -0.07
     syk
    -0.07
     ফুল
    -0.07
    ությունները
    -0.07
    POSITIVE LOGITS
     modificación
    0.08
     transformación
    0.08
     generation
    0.08
     unus
    0.07
     overcrow
    0.07
     imposible
    0.07
    ಾಗಿ
    0.07
     Funktion
    0.07
    Generation
    0.07
     einer
    0.07
    Activations Density 0.001%

    No Known Activations