© 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. 23-RESID-POST-AA
    11. 50762
    Prev
    Next
    INDEX
    Explanations

    wood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Però
    -0.08
     Nội
    -0.08
     Narr
    -0.08
     narratives
    -0.08
     Customs
    -0.08
     blown
    -0.08
     narr
    -0.08
     breached
    -0.07
     Cabe
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    -specific
    0.12
     screws
    0.11
    -safe
    0.10
     conditioner
    0.10
     se
    0.09
     lubricant
    0.09
     put
    0.09
     alcohol
    0.09
     flour
    0.09
     seasoning
    0.09
    Activations Density 0.008%

    No Known Activations