Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120278
    Prev
    Next
    INDEX
    Explanations

    Numerical ranges and intervals

    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
    Famil
    -0.08
    _sequence
    -0.08
    נסה
    -0.08
     familial
    -0.08
    _SEQUENCE
    -0.07
    Animated
    -0.07
     minimal
    -0.07
    sequence
    -0.07
    κ
    -0.07
    Immer
    -0.07
    POSITIVE LOGITS
     영역
    0.11
    二区
    0.10
     subdivisions
    0.10
     subdiv
    0.10
    uckets
    0.09
     adulthood
    0.09
    三区
    0.09
     buckets
    0.09
     mezz
    0.08
     이후
    0.08
    Activations Density 0.023%

    No Known Activations