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. 23164
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     */↵/
    -0.09
    VIDIA
    -0.07
    काम
    -0.07
    तः
    -0.07
     Besch
    -0.07
     erupted
    -0.07
     सप्त
    -0.07
    796
    -0.07
     يحتوي
    -0.07
    ավորապես
    -0.07
    POSITIVE LOGITS
     thereby
    0.08
     democrat
    0.08
    highlight
    0.08
     더욱
    0.08
     fascinating
    0.08
     이는
    0.08
     vastly
    0.08
     conforme
    0.08
     fostering
    0.07
     driven
    0.07
    Activations Density 0.165%

    No Known Activations