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. 42964
    Prev
    Next
    INDEX
    Explanations

    context

    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
     הגדול
    -0.08
    B
    -0.08
     staircase
    -0.08
     anzeigen
    -0.08
    满
    -0.08
    Eye
    -0.07
    aidu
    -0.07
    Position
    -0.07
     vy
    -0.07
     previously
    -0.07
    POSITIVE LOGITS
    /context
    0.10
    =context
    0.09
    .Environment
    0.09
     환경
    0.09
    .Glide
    0.08
     ctx
    0.08
    .Context
    0.08
     Bless
    0.08
    ctx
    0.08
    .databinding
    0.08
    Activations Density 0.002%

    No Known Activations