© 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. 47587
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
     enhance
    -0.08
    性生活
    -0.07
     elic
    -0.07
     Roberts
    -0.07
    ાત્મક
    -0.07
    úc
    -0.07
     sing
    -0.07
     happening
    -0.07
    plaintext
    -0.07
     pleinement
    -0.07
    POSITIVE LOGITS
     away
    0.15
    距离
    0.14
    Away
    0.14
     Away
    0.13
     ದೂರ
    0.13
     بعيد
    0.13
     distancia
    0.13
     দূ
    0.13
    _distance
    0.13
    远
    0.12
    Activations Density 0.058%

    No Known Activations