© 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 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. 69386
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     volum
    -0.08
     vect
    -0.07
     செல்ல
    -0.07
     summit
    -0.07
     certainty
    -0.07
     ce
    -0.07
     ஸ
    -0.07
     unten
    -0.07
     Beitr
    -0.07
    +')
    -0.07
    POSITIVE LOGITS
    ynomials
    0.09
     filmes
    0.08
    лова
    0.08
     фильмы
    0.08
    imonio
    0.08
    колько
    0.08
     Zwolle
    0.08
    렇게
    0.08
    ubwo
    0.08
    يران
    0.08
    Activations Density 0.020%

    No Known Activations