© 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. 19256
    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
     downloaded
    -0.09
     positive
    -0.09
     healed
    -0.08
    positive
    -0.08
     colspan
    -0.08
     filled
    -0.08
     fertig
    -0.08
     completed
    -0.08
     pozitiv
    -0.08
     regenerated
    -0.07
    POSITIVE LOGITS
     noticing
    0.12
     acknowledging
    0.11
     practice
    0.11
     pause
    0.11
     acknowledge
    0.11
    练
    0.11
    _ack
    0.11
    .pause
    0.10
    Pause
    0.10
    暂停
    0.10
    Activations Density 0.014%

    No Known Activations