© 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. 47518
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
     यहां
    -0.32
     जहां
    -0.32
     हूं
    -0.32
     বিষয়
    -0.28
     দিয়ে
    -0.28
     आंख
    -0.27
     দেয়
    -0.27
     সময়
    -0.27
     হয়
    -0.26
     দিয়
    -0.26
    POSITIVE LOGITS
    ুয়ারি
    0.23
    ೀ
    0.22
    ೇ
    0.21
     എന്നിവര്
    0.20
     छोड़
    0.20
     लड़
    0.20
     آئی
    0.19
     बड़े
    0.19
     बड़ी
    0.19
    ুয়ার
    0.19
    Activations Density 0.275%

    No Known Activations