© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18536
    Prev
    Next
    INDEX
    Explanations

    in

    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
     in
    -0.12
     在
    -0.11
     katika
    -0.11
     في
    -0.11
     trong
    -0.11
     mewn
    -0.10
     idar
    -0.10
     în
    -0.10
     inay
    -0.10
     në
    -0.09
    POSITIVE LOGITS
     terms
    0.11
     general
    0.11
     absence
    0.10
     theory
    0.10
    fty
    0.10
     assumption
    0.10
     entirety
    0.10
     presence
    0.10
     usual
    0.09
     expression
    0.09
    Activations Density 0.044%

    No Known Activations