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. 74445
    Prev
    Next
    INDEX
    Explanations

    particular

    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
     гэж
    -0.09
    משיך
    -0.09
     આવ્યું
    -0.09
     وکړئ
    -0.09
     mmasị
    -0.08
     predicament
    -0.08
     freue
    -0.08
     બનાવી
    -0.08
     发表于
    -0.08
    ,今年
    -0.08
    POSITIVE LOGITS
    ternative
    0.08
    fic
    0.07
    perc
    0.07
    grp
    0.07
    alts
    0.07
    lectric
    0.07
     corpor
    0.07
    inary
    0.07
     anche
    0.07
     cui
    0.07
    Activations Density 0.036%

    No Known Activations