© 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 EvalsExportsinterp-engineNEWAPI 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. 18839
    Prev
    Next
    INDEX
    Explanations

    Chinese academic texts

    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
    словия
    -0.09
    哪些
    -0.09
    _conditions
    -0.09
     verschiedenen
    -0.09
    Conditions
    -0.08
     వంటి
    -0.08
     जैसे
    -0.08
     conditions
    -0.08
    conditions
    -0.08
    libraries
    -0.08
    POSITIVE LOGITS
     آهي
    0.13
    。其中
    0.12
     것입니다
    0.12
    ವಾಗಿದೆ
    0.12
    ，它
    0.12
    입니다
    0.12
    。如果
    0.11
    ಾಗಿದೆ
    0.11
    综合在线
    0.11
    目です
    0.11
    Activations Density 0.028%

    No Known Activations