© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19446
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第一次
    -0.10
     first
    -0.10
    	first
    -0.10
    'abord
    -0.09
     сначала
    -0.09
     pertama
    -0.09
    ’abord
    -0.09
     два
    -0.09
     पहली
    -0.09
     firstly
    -0.09
    POSITIVE LOGITS
    999
    0.13
     النهائي
    0.13
     النهاية
    0.13
    Final
    0.13
     Finale
    0.12
     Final
    0.12
     기타
    0.12
    _final
    0.12
     Bonus
    0.11
     BONUS
    0.11
    Activations Density 0.025%

    No Known Activations