Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49314
    Prev
    Next
    INDEX
    Explanations

    file types

    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
     provenientes
    -0.08
    Got
    -0.07
     Nee
    -0.07
    र्फ
    -0.07
    -cig
    -0.07
    got
    -0.07
    gebnisse
    -0.07
     puzz
    -0.07
    েগ
    -0.07
     जिसके
    -0.07
    POSITIVE LOGITS
     someday
    0.08
     файл
    0.08
     kayan
    0.08
     yüks
    0.07
     vient
    0.07
    .&
    0.07
     përd
    0.07
    .make
    0.07
     યાદ
    0.07
    .Col
    0.07
    Activations Density 0.004%

    No Known Activations