© 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. 19613
    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
     wouldnt
    -0.11
     possam
    -0.10
     poderiam
    -0.10
     olmay
    -0.10
     könnten
    -0.10
     magari
    -0.09
     wouldn't
    -0.09
    abilece
    -0.09
     podrían
    -0.09
     možda
    -0.09
    POSITIVE LOGITS
    です
    0.19
     합니다
    0.18
    しています
    0.18
    합니다
    0.18
    입니다
    0.17
    します
    0.17
     있습니다
    0.16
    했습니다
    0.16
     байна
    0.16
     आहे
    0.16
    Activations Density 0.005%

    No Known Activations