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. 53257
    Prev
    Next
    INDEX
    Explanations

    submission

    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
     Unary
    -0.09
     indulge
    -0.08
    wend
    -0.08
     unary
    -0.07
     WALK
    -0.07
     tag
    -0.07
     listop
    -0.07
     ,
    -0.07
     itong
    -0.07
     développ
    -0.07
    POSITIVE LOGITS
     제출
    0.14
     জম
    0.12
    提交
    0.11
    上传
    0.11
     enviada
    0.11
     upload
    0.11
    Uploading
    0.11
    .upload
    0.11
     ಸಲ್ಲ
    0.11
     uploading
    0.11
    Activations Density 0.040%

    No Known Activations