© 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. 11-RESID-POST-AA
    11. 64759
    Prev
    Next
    INDEX
    Explanations

    kaggle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htdocs
    -0.07
     carteira
    -0.07
     '.',
    -0.07
     dotted
    -0.07
     nieuwsg
    -0.07
     pastoral
    -0.07
     journée
    -0.07
     countertop
    -0.07
     deceive
    -0.07
    /work
    -0.07
    POSITIVE LOGITS
     Aquí
    0.08
    icaragua
    0.07
     estab
    0.07
     erfü
    0.07
    definitions
    0.07
     emplacement
    0.07
     Zar
    0.07
     offending
    0.07
     appart
    0.07
    紧
    0.07
    Activations Density 0.000%

    No Known Activations