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. 112842
    Prev
    Next
    INDEX
    Explanations

    story generation

    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
     retailers
    -0.08
    수를
    -0.07
     bosses
    -0.07
     agot
    -0.07
     Wait
    -0.07
     atras
    -0.07
     Δ
    -0.07
     spline
    -0.07
     Delta
    -0.07
    Delta
    -0.07
    POSITIVE LOGITS
     companionship
    0.11
     amic
    0.10
     yosh
    0.10
     gemeinsam
    0.09
     معهم
    0.09
     amizade
    0.09
     đoàn
    0.09
     stewardship
    0.09
    ร่วม
    0.09
    建立
    0.08
    Activations Density 0.058%

    No Known Activations