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. 130876
    Prev
    Next
    INDEX
    Explanations

    "free" in other 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
     scarcely
    -0.09
    Interrupted
    -0.09
     тяж
    -0.08
     schwier
    -0.08
    طيط
    -0.08
     сложно
    -0.08
     faudrait
    -0.08
     demasi
    -0.08
     δύσ
    -0.08
     relying
    -0.08
    POSITIVE LOGITS
     मुफ्त
    0.28
     zdarma
    0.27
    免费
    0.27
     gratis
    0.27
    免費
    0.26
     бесплат
    0.26
     무료
    0.26
     бесплатно
    0.26
     免费
    0.25
     مجاني
    0.25
    Activations Density 0.230%

    No Known Activations