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. 43275
    Prev
    Next
    INDEX
    Explanations

    Various types of written content

    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
     אינו
    -0.08
     טבע
    -0.08
     עושה
    -0.07
     Selle
    -0.07
     germs
    -0.07
     nearby
    -0.07
     tangible
    -0.07
     دين
    -0.07
     previa
    -0.07
     altar
    -0.07
    POSITIVE LOGITS
     Luft
    0.08
    лем
    0.07
    esteps
    0.07
     folie
    0.07
     Fin
    0.07
     amab
    0.07
     konflik
    0.07
     amelyek
    0.07
     રહ
    0.07
    /licenses
    0.07
    Activations Density 0.000%

    No Known Activations