© 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. 19-RESID-POST-AA
    11. 103475
    Prev
    Next
    INDEX
    Explanations

    Exiting

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    īgu
    -0.08
    background
    -0.08
     నేప
    -0.08
    央视
    -0.08
    λλην
    -0.08
    laub
    -0.08
    ;background
    -0.08
     miền
    -0.08
    电脑版
    -0.08
    -Bl
    -0.08
    POSITIVE LOGITS
     keluar
    0.21
    خرج
    0.20
     বের
    0.19
     வெளிய
    0.19
     કાઢ
    0.19
     выйти
    0.18
     उतर
    0.18
     exiting
    0.18
     બહાર
    0.18
    _out
    0.18
    Activations Density 0.045%

    No Known Activations