© 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 EvalsExportsAPI 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. 19847
    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
     jarenlang
    -0.10
     saepe
    -0.09
    ometimes
    -0.08
     vostru
    -0.08
     krijg
    -0.08
    окуп
    -0.08
     dealerships
    -0.08
     怎
    -0.08
    ESOME
    -0.08
     чаще
    -0.08
    POSITIVE LOGITS
     contraind
    0.21
     противопоказ
    0.18
     pregnancy
    0.13
     intolerance
    0.12
    contra
    0.12
     Contra
    0.12
     inability
    0.12
     pregnant
    0.12
     allergic
    0.12
     prohib
    0.12
    Activations Density 0.005%

    No Known Activations