© 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. 103200
    Prev
    Next
    INDEX
    Explanations

    to

    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
     can
    -0.10
     వంటి
    -0.10
    .↵↵
    -0.09
     due
    -0.09
    .,
    -0.09
    など
    -0.09
    等
    -0.09
    甚至
    -0.08
    ،
    -0.08
     owing
    -0.08
    POSITIVE LOGITS
     your
    0.13
     specifications
    0.13
     Specifications
    0.12
     guidelines
    0.11
    Specifications
    0.11
    ايير
    0.11
     Standards
    0.11
     standards
    0.10
    你的
    0.10
     estándares
    0.10
    Activations Density 0.022%

    No Known Activations