© 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. 102469
    Prev
    Next
    INDEX
    Explanations

    Muhammad

    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
     תש
    -0.08
     deciding
    -0.08
     airfare
    -0.07
    岛国
    -0.07
     décide
    -0.07
    /write
    -0.07
     karar
    -0.07
    creens
    -0.07
    uchi
    -0.07
     կ
    -0.07
    POSITIVE LOGITS
     صلى
    0.20
     ﷺ
    0.15
     صلی
    0.11
     رسول
    0.10
     Messenger
    0.10
     boodsch
    0.09
     messenger
    0.09
     മുഹ
    0.08
     integrity
    0.08
     محمد
    0.08
    Activations Density 0.008%

    No Known Activations