© 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. 18938
    Prev
    Next
    INDEX
    Explanations

    careful calculation

    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
     these
    -0.12
     this
    -0.11
    These
    -0.10
     THIS
    -0.10
     этой
    -0.10
    these
    -0.09
    This
    -0.09
     این
    -0.09
    これ
    -0.09
     These
    -0.08
    POSITIVE LOGITS
     deserves
    0.15
     tricky
    0.12
     വീണ്ടും
    0.12
     clarification
    0.12
     careful
    0.12
     calculation
    0.11
     genauer
    0.11
     sorgfält
    0.11
     Calculation
    0.11
     مزید
    0.11
    Activations Density 0.044%

    No Known Activations