© 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. 103517
    Prev
    Next
    INDEX
    Explanations

    Non-alphanumeric characters

    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
     if
    -0.09
     though
    -0.08
     such
    -0.08
    itaanka
    -0.07
    font
    -0.07
    فة
    -0.07
    -headed
    -0.07
    떤
    -0.07
     اگر
    -0.07
     whether
    -0.07
    POSITIVE LOGITS
    ®
    0.11
    �讯
    0.09
    �除
    0.09
     ella
    0.09
     ellas
    0.09
    /right
    0.08
    ово
    0.08
    ™
    0.08
     /
    0.08
    unn
    0.08
    Activations Density 0.913%

    No Known Activations