© 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. 91565
    Prev
    Next
    INDEX
    Explanations

    Fahrenheit 451

    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
     tỷ
    -0.08
    adzirisa
    -0.08
     Quy
    -0.08
    ummen
    -0.07
     transparencia
    -0.07
     reagent
    -0.07
     reform
    -0.07
     tsum
    -0.07
     qey
    -0.07
     Cosmetic
    -0.07
    POSITIVE LOGITS
     Plato
    0.10
     الحض
    0.09
     advocating
    0.08
     Fahrenheit
    0.08
     Nobel
    0.08
     культуры
    0.08
     complac
    0.08
     advocate
    0.08
     ninety
    0.08
     Jupiter
    0.08
    Activations Density 0.003%

    No Known Activations