© 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. 19706
    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
    Solutions
    -0.09
    Solution
    -0.08
    construction
    -0.08
    Damage
    -0.08
     hoher
    -0.08
    Development
    -0.08
    Machine
    -0.08
    Construction
    -0.08
    もう
    -0.08
     العمل
    -0.08
    POSITIVE LOGITS
     lit
    0.11
    -lit
    0.11
    hearted
    0.09
     corridor
    0.09
     gehouden
    0.09
     corridors
    0.09
     evening
    0.09
     wooded
    0.09
     hallway
    0.09
     afternoon
    0.08
    Activations Density 0.001%

    No Known Activations