© 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. 108186
    Prev
    Next
    INDEX
    Explanations

    magic spells, age regression

    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
     procesamiento
    -0.09
     ය
    -0.09
    ਿੰਦ
    -0.08
    未经
    -0.08
     имеется
    -0.08
    无需
    -0.08
     ponerse
    -0.08
    orwa
    -0.08
     معالجة
    -0.08
    وظ
    -0.08
    POSITIVE LOGITS
     quadr
    0.08
    grader
    0.08
     plateau
    0.08
     Plateau
    0.08
     enemies
    0.08
     Dyson
    0.07
    autore
    0.07
    grad
    0.07
     Orb
    0.07
     coefficient
    0.07
    Activations Density 0.002%

    No Known Activations