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. 76507
    Prev
    Next
    INDEX
    Explanations

    P

    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
    LOD
    -0.08
    quil
    -0.08
     Nicholson
    -0.08
     unnoticed
    -0.08
    yond
    -0.08
     kasar
    -0.08
     khỏi
    -0.07
     bino
    -0.07
     kỹ
    -0.07
     onderscheid
    -0.07
    POSITIVE LOGITS
     Fiat
    0.08
     Palacio
    0.08
    [-
    0.07
     Hed
    0.07
    สิ
    0.07
     hormones
    0.07
    otherapeut
    0.07
    -decoration
    0.07
     stimulation
    0.07
     VH
    0.07
    Activations Density 0.002%

    No Known Activations