© 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. 23-RESID-POST-AA
    11. 49307
    Prev
    Next
    INDEX
    Explanations

    Steel

    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
    Appartement
    -0.09
     arrested
    -0.09
     Badezimmer
    -0.09
     badkamer
    -0.09
    atedral
    -0.08
     Packed
    -0.08
     exfol
    -0.08
     vietnam
    -0.08
     browned
    -0.08
    ------+
    -0.08
    POSITIVE LOGITS
    牌
    0.12
    合
    0.10
    等
    0.09
     coa
    0.09
     ग्र
    0.09
     ગ્ર
    0.08
     등
    0.08
     grades
    0.08
     carte
    0.08
     合
    0.08
    Activations Density 0.004%

    No Known Activations