© 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. 19435
    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
     deepest
    -0.09
     সবচ
    -0.09
     supposed
    -0.09
     They
    -0.09
     સૌથી
    -0.09
     pinakam
    -0.09
     najman
    -0.08
     pinaka
    -0.08
     pinakamahusay
    -0.08
     ең
    -0.08
    POSITIVE LOGITS
                   ↵
    0.09
    vyš
    0.08
    cris
    0.08
    ream
    0.08
    선을
    0.08
    -utils
    0.08
    ��
    0.08
     võtta
    0.07
    encji
    0.07
    종
    0.07
    Activations Density 0.050%

    No Known Activations