© 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. 18777
    Prev
    Next
    INDEX
    Explanations

    Language-related words

    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
    �ે
    -0.09
    এই
    -0.09
    -loaded
    -0.08
    আই
    -0.08
    -mentioned
    -0.08
    ন্টার
    -0.08
     vyd
    -0.08
    서비스
    -0.08
     whereby
    -0.08
    আম
    -0.08
    POSITIVE LOGITS
    語
    0.13
    语
    0.12
    人
    0.12
    人在
    0.11
    人的
    0.11
    族
    0.11
    ischer
    0.11
    երեն
    0.10
    ர்கள
    0.10
     ഭാഷ
    0.09
    Activations Density 0.004%

    No Known Activations