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. 88355
    Prev
    Next
    INDEX
    Explanations

    pig

    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
    ต้น
    -0.08
     inhibitory
    -0.08
     Lev
    -0.07
     haine
    -0.07
     Hao
    -0.07
     Chakra
    -0.07
    ӣ
    -0.07
     hap
    -0.07
     Gun
    -0.07
    ć
    -0.07
    POSITIVE LOGITS
     pigs
    0.07
     참여
    0.07
     agriculture
    0.07
     참가
    0.07
     onderzoek
    0.07
    �
    0.07
     недвижимости
    0.07
     పాల్గ
    0.07
     বিজ্ঞ
    0.07
     तेजी
    0.07
    Activations Density 0.004%

    No Known Activations