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. 97079
    Prev
    Next
    INDEX
    Explanations

    value (all 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
     devrez
    -0.10
     doit
    -0.10
     harus
    -0.09
     devez
    -0.09
     devra
    -0.09
     doivent
    -0.09
     해야
    -0.08
     deben
    -0.08
     Must
    -0.08
     moet
    -0.08
    POSITIVE LOGITS
     value
    0.33
     valore
    0.29
     valorar
    0.29
    价值
    0.29
    value
    0.28
     appreciate
    0.28
     değer
    0.28
     values
    0.28
     విల
    0.27
    価
    0.27
    Activations Density 0.146%

    No Known Activations