© 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. 44474
    Prev
    Next
    INDEX
    Explanations

    Anime references

    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
     curb
    -0.09
     installers
    -0.08
     ballast
    -0.08
     invoices
    -0.08
     astronomical
    -0.08
     işlet
    -0.08
     cookware
    -0.08
     installer
    -0.08
     ASTM
    -0.08
     manufacturers
    -0.08
    POSITIVE LOGITS
     Naruto
    0.10
     Defense
    0.10
     ninja
    0.09
     defense
    0.09
    Defense
    0.09
     Fortnite
    0.09
    ulti
    0.08
     دفاع
    0.08
     verded
    0.08
     defenders
    0.08
    Activations Density 0.010%

    No Known Activations