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. 106062
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
    ારી
    -0.08
    .Ab
    -0.08
    ારીઓ
    -0.08
     tui
    -0.07
     EPC
    -0.07
    mtp
    -0.07
    agir
    -0.07
    Ab
    -0.07
    орист
    -0.07
     επικ
    -0.07
    POSITIVE LOGITS
     выт
    0.08
     sowohl
    0.08
     pent
    0.08
     empfe
    0.07
     carn
    0.07
     hex
    0.07
     dalla
    0.07
    6
    0.07
    gement
    0.07
     Opportunity
    0.07
    Activations Density 0.035%

    No Known Activations