© 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. 21975
    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
     kaikki
    -0.10
     each
    -0.10
     all
    -0.09
     всех
    -0.09
     is
    -0.09
     все
    -0.09
     semua
    -0.08
     جميع
    -0.08
     всички
    -0.08
     барлық
    -0.08
    POSITIVE LOGITS
     taki
    0.09
    efi
    0.08
    ↓↵↵
    0.08
     conocemos
    0.08
    	Type
    0.07
     deux
    0.07
    ，引
    0.07
    ：約
    0.07
    ૨
    0.07
    _align
    0.07
    Activations Density 0.000%

    No Known Activations