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. 106071
    Prev
    Next
    INDEX
    Explanations

    20

    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
     Peek
    -0.09
    tong
    -0.08
    धिक
    -0.08
     küs
    -0.08
     bekend
    -0.08
     Peaks
    -0.08
    胡
    -0.08
     kwenye
    -0.08
     toe
    -0.08
    naz
    -0.08
    POSITIVE LOGITS
     gradually
    0.08
     importantly
    0.08
     configuration
    0.08
    -high
    0.08
     progressively
    0.08
    -padding
    0.08
    -home
    0.08
    -around
    0.08
     padding
    0.07
     haute
    0.07
    Activations Density 0.002%

    No Known Activations