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. 49795
    Prev
    Next
    INDEX
    Explanations

    try

    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
     사항
    -0.10
    사항
    -0.08
     cherished
    -0.08
     услов
    -0.07
     cr
    -0.07
     '-
    -0.07
    事項
    -0.07
     hük
    -0.07
     béton
    -0.07
     esigen
    -0.07
    POSITIVE LOGITS
     malicious
    0.09
     deceit
    0.09
    骗
    0.08
     Fil
    0.08
     deception
    0.08
     Mal
    0.08
    cdf
    0.08
    אמ
    0.08
     Ам
    0.08
     cunning
    0.07
    Activations Density 0.006%

    No Known Activations