© 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. 23-RESID-POST-AA
    11. 50998
    Prev
    Next
    INDEX
    Explanations

    Adhesion

    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
    NSDate
    -0.08
    ‌మ
    -0.08
    Divider
    -0.08
     peserta
    -0.08
    xls
    -0.08
     pihak
    -0.08
     interdum
    -0.07
    átor
    -0.07
     namp
    -0.07
    řit
    -0.07
    POSITIVE LOGITS
    着
    0.13
    附
    0.11
    結
    0.10
    著
    0.10
    连
    0.10
    連
    0.10
    结
    0.10
    性
    0.09
     kết
    0.09
    合作
    0.09
    Activations Density 0.001%

    No Known Activations