© 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. 102268
    Prev
    Next
    INDEX
    Explanations

    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
    ��
    -0.09
     lẹhin
    -0.09
    уын
    -0.08
    incerely
    -0.08
     కొత్త
    -0.08
     Say
    -0.08
    ��
    -0.08
    авання
    -0.08
    concat
    -0.08
    ��
    -0.08
    POSITIVE LOGITS
     difference
    0.16
     verschil
    0.15
     différence
    0.13
     diferença
    0.13
     Unterschied
    0.13
    差
    0.13
    _difference
    0.13
    difference
    0.13
     differences
    0.12
     اختلاف
    0.12
    Activations Density 0.022%

    No Known Activations