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. 46104
    Prev
    Next
    INDEX
    Explanations

    ith

    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
    combined
    -0.09
    адки
    -0.07
     disabled
    -0.07
    disabled
    -0.07
    latin
    -0.07
     dragged
    -0.07
     વગેરે
    -0.07
     personalised
    -0.07
     combined
    -0.07
    әр
    -0.07
    POSITIVE LOGITS
     जल्दी
    0.09
    迅
    0.08
     GUAR
    0.08
    Mbps
    0.08
     schneller
    0.08
    -paced
    0.07
     aient
    0.07
     liquidity
    0.07
    ,截至
    0.07
     monopol
    0.07
    Activations Density 0.000%

    No Known Activations