© 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. 97577
    Prev
    Next
    INDEX
    Explanations

    Overheating

    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
    -independent
    -0.08
     trag
    -0.08
     dezembro
    -0.07
    (at
    -0.07
    ाद
    -0.07
    582
    -0.07
     independent
    -0.07
     american
    -0.07
     mă
    -0.06
     अमेरिका
    -0.06
    POSITIVE LOGITS
    tage
    0.09
    Invert
    0.09
     وذلك
    0.08
    AVI
    0.08
    ktor
    0.08
     kohe
    0.08
    ↓↵↵
    0.08
    ząt
    0.08
    는데
    0.08
    iência
    0.08
    Activations Density 0.000%

    No Known Activations