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. 117623
    Prev
    Next
    INDEX
    Explanations

    negative-sense RNA viruses

    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
    拓
    -0.08
     refine
    -0.08
    ocument
    -0.08
    推广
    -0.07
     招
    -0.07
    人工
    -0.07
     hany
    -0.07
    _APPRO
    -0.07
    ugen
    -0.07
     Caldwell
    -0.07
    POSITIVE LOGITS
    FORMAT
    0.08
     семья
    0.08
     ül
    0.08
     pamilya
    0.08
     dancer
    0.08
     familias
    0.08
     neurosc
    0.08
     стране
    0.08
    famil
    0.08
     фестив
    0.08
    Activations Density 0.001%

    No Known Activations