© 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. 103493
    Prev
    Next
    INDEX
    Explanations

    spawn/awns

    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
    掲載
    -0.10
    發布
    -0.09
    ublishing
    -0.08
     staining
    -0.08
     ontdekt
    -0.08
     saada
    -0.08
    'utilisation
    -0.08
     penggunaan
    -0.08
     gepubliceerd
    -0.08
     outubro
    -0.08
    POSITIVE LOGITS
     copies
    0.11
     into
    0.10
     predefined
    0.10
     clones
    0.10
     instances
    0.09
    copies
    0.09
     defenders
    0.09
     enemies
    0.09
     anew
    0.09
    Copies
    0.09
    Activations Density 0.003%

    No Known Activations