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. 24388
    Prev
    Next
    INDEX
    Explanations

    the

    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
     subj
    -0.09
    हरू
    -0.08
    Gravity
    -0.07
     usar
    -0.07
     redes
    -0.07
    हरूको
    -0.07
     algunas
    -0.07
    weza
    -0.07
     сф
    -0.07
     diẹ
    -0.07
    POSITIVE LOGITS
    buyer
    0.10
     Trends
    0.10
     spécialiste
    0.09
     trends
    0.09
     روند
    0.09
    exports
    0.09
    cycles
    0.09
     distributor
    0.08
     тенден
    0.08
    pricing
    0.08
    Activations Density 0.024%

    No Known Activations