© 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. 23-RESID-POST-AA
    11. 47710
    Prev
    Next
    INDEX
    Explanations

    Q

    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
     vrijdag
    -0.09
     Cinco
    -0.09
     ఐ
    -0.09
     Comcast
    -0.08
     ಐ
    -0.08
     friday
    -0.08
    ="[
    -0.08
     শুক্রবার
    -0.08
    țiile
    -0.08
     Friday
    -0.08
    POSITIVE LOGITS
    MS
    0.19
     MS
    0.15
    ms
    0.14
     ms
    0.12
    SMS
    0.11
    	ms
    0.11
    _MS
    0.11
    МС
    0.10
    -MS
    0.10
    MB
    0.10
    Activations Density 0.001%

    No Known Activations