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. 15-RESID-POST-AA
    6. 19704
    Prev
    Next
    INDEX
    Explanations

    special

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anat
    -0.10
     hike
    -0.09
     hikes
    -0.08
    forget
    -0.08
     glacier
    -0.08
     volumes
    -0.08
     Vineyard
    -0.08
    dyn
    -0.08
    dynamic
    -0.08
     peb
    -0.08
    POSITIVE LOGITS
     punctuation
    0.14
    _symbols
    0.13
     symbols
    0.13
    Symbols
    0.12
     Symbols
    0.12
     símbolos
    0.12
     ASCII
    0.12
     ascii
    0.11
    _ascii
    0.11
    ASCII
    0.11
    Activations Density 0.007%

    No Known Activations