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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49211
    Prev
    Next
    INDEX
    Explanations

    Notepad++ and functions

    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
     quand
    -0.09
    qu
    -0.07
    幻想
    -0.07
     Ende
    -0.07
    führen
    -0.07
    ási
    -0.07
    imated
    -0.07
     क्व
    -0.07
    auspiel
    -0.07
     astuces
    -0.07
    POSITIVE LOGITS
     அதன்
    0.08
    akarta
    0.08
     Nordic
    0.08
    /libs
    0.07
     kul
    0.07
     suelo
    0.07
     Old
    0.07
     Guardia
    0.07
     kuf
    0.07
     течение
    0.07
    Activations Density 0.001%

    No Known Activations