© 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. 18659
    Prev
    Next
    INDEX
    Explanations

    defining the meaning

    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
     դրանց
    -0.08
    ात्म
    -0.08
     համապատասխան
    -0.08
    ổ
    -0.08
    ику
    -0.08
    /oder
    -0.08
    åde
    -0.08
    નાઓ
    -0.08
     doorga
    -0.08
     daarna
    -0.08
    POSITIVE LOGITS
     where
    0.15
    という
    0.14
     şekl
    0.13
     indicating
    0.13
     എന്ന
    0.13
     implying
    0.13
     అనే
    0.13
     wherein
    0.13
     എന്നാണ്
    0.12
     This
    0.12
    Activations Density 0.049%

    No Known Activations