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. 60910
    Prev
    Next
    INDEX
    Explanations

    legal penalties

    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
    想
    -0.08
     mismatch
    -0.08
     جهة
    -0.07
    稍
    -0.07
     الجودة
    -0.07
     pathlib
    -0.07
    -nowrap
    -0.07
    حل
    -0.07
     الهدف
    -0.07
     উদ্দেশ
    -0.07
    POSITIVE LOGITS
     lawsuits
    0.12
     bankruptcy
    0.10
     cease
    0.10
     lawsuit
    0.09
    ậm
    0.09
     notor
    0.09
     bankrupt
    0.09
     veröff
    0.09
    endaftaran
    0.09
     disg
    0.09
    Activations Density 0.017%

    No Known Activations