© 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. 20183
    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
     반환
    -0.10
     produjo
    -0.09
     producing
    -0.09
     devuelve
    -0.09
    üren
    -0.08
     undertaking
    -0.08
    езульт
    -0.08
     ראשון
    -0.08
    อันดับ
    -0.08
     ניצ
    -0.08
    POSITIVE LOGITS
     mention
    0.13
     avoid
    0.13
     better
    0.12
     avoids
    0.12
     vague
    0.12
     subtly
    0.12
     leave
    0.12
     simpler
    0.12
     mentions
    0.11
     erwäh
    0.11
    Activations Density 0.059%

    No Known Activations