© 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. 102562
    Prev
    Next
    INDEX
    Explanations

    Rounding numbers

    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
     বাস্ত
    -0.08
     haqqında
    -0.08
     sağ
    -0.08
     ongeveer
    -0.07
    �
    -0.07
     туралы
    -0.07
     nagyon
    -0.07
     Teng
    -0.07
     이러한
    -0.07
     extremely
    -0.07
    POSITIVE LOGITS
     округ
    0.12
     unchanged
    0.11
     rounding
    0.11
    舍
    0.10
     increment
    0.10
     જશે
    0.10
     rounded
    0.10
     जाएगी
    0.09
     ceil
    0.09
     downg
    0.09
    Activations Density 0.009%

    No Known Activations