© 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. 45670
    Prev
    Next
    INDEX
    Explanations

    delimiters

    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
     gond
    -0.08
    170
    -0.07
     від
    -0.07
    �
    -0.07
    ancar
    -0.07
    無
    -0.07
     eş
    -0.07
    我
    -0.07
     actually
    -0.07
    實
    -0.07
    POSITIVE LOGITS
    DIM
    0.08
    નિવ
    0.08
    awdd
    0.08
     diejenigen
    0.08
     بالإضافة
    0.08
    alai
    0.08
    ementara
    0.08
     Zusätzlich
    0.08
    ಭವ
    0.08
     mussten
    0.08
    Activations Density 0.047%

    No Known Activations