© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94923
    Prev
    Next
    INDEX
    Explanations

    physics and scientific theories

    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
     पैसे
    -0.09
     lav
    -0.08
    lov
    -0.08
     wines
    -0.08
     millions
    -0.08
     thousands
    -0.08
     monetize
    -0.08
     stump
    -0.08
     funds
    -0.08
    sav
    -0.07
    POSITIVE LOGITS
     forb
    0.10
     upheld
    0.09
     maksimum
    0.09
    禁止
    0.09
     velocidad
    0.09
    കാശ
    0.09
     Uph
    0.09
     حماية
    0.09
     schützt
    0.09
     سرعة
    0.08
    Activations Density 0.002%

    No Known Activations