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. 65243
    Prev
    Next
    INDEX
    Explanations

    three

    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
     Independ
    -0.08
     estable
    -0.08
    将
    -0.07
    -0.07
     review
    -0.07
    Emb
    -0.07
     INNER
    -0.07
    mith
    -0.07
     Intent
    -0.07
     Milo
    -0.07
    POSITIVE LOGITS
    �↵↵
    0.08
     이상의
    0.08
     Kooperation
    0.08
     kabel
    0.07
     கூட
    0.07
     이상
    0.07
     Beaumont
    0.07
     acqua
    0.07
     કરતાં
    0.07
     opvall
    0.07
    Activations Density 0.047%

    No Known Activations