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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130739
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acute
    -0.08
    аса
    -0.08
    енн
    -0.08
    өш
    -0.08
     continually
    -0.08
    Graphic
    -0.07
    ­ge
    -0.07
    vert
    -0.07
     queim
    -0.07
     ausgeschlossen
    -0.07
    POSITIVE LOGITS
    Labor
    0.08
     Labour
    0.08
    Dinner
    0.08
     nipa
    0.08
     Labor
    0.08
     DISPLAY
    0.07
    ikia
    0.07
    stid
    0.07
     kats
    0.07
     εργασ
    0.07
    Activations Density 0.000%

    No Known Activations