© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 48994
    Prev
    Next
    INDEX
    Explanations

    高

    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
    -Friendly
    -0.08
    RIEND
    -0.08
     balans
    -0.08
     bespre
    -0.08
     bueno
    -0.07
     bah
    -0.07
     amigo
    -0.07
    -hi
    -0.07
    -needed
    -0.07
     unusually
    -0.07
    POSITIVE LOGITS
    等
    0.13
     institutions
    0.11
    כלה
    0.11
     instituições
    0.10
    院
    0.10
     judiciary
    0.10
     等
    0.10
    -eche
    0.09
    انوية
    0.09
    صیلات
    0.09
    Activations Density 0.007%

    No Known Activations