© 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. 103425
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ്രമ
    -0.08
     فلا
    -0.08
    :↵↵↵
    -0.08
     jd
    -0.07
     ندارد
    -0.07
     jit
    -0.07
     ritmo
    -0.07
    ("")){↵
    -0.07
     ted
    -0.07
    ，否则
    -0.07
    POSITIVE LOGITS
     ซึ่ง
    0.10
    orações
    0.09
     אשר
    0.09
     ?↵
    0.09
    ọdọ
    0.09
    óveis
    0.08
     וואָס
    0.08
     WHICH
    0.08
     Sinds
    0.08
    ordeeld
    0.08
    Activations Density 0.190%

    No Known Activations