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. 12143
    Prev
    Next
    INDEX
    Explanations

    diagonal

    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
     gather
    -0.09
     veterans
    -0.08
     gathered
    -0.08
     paternal
    -0.08
     garn
    -0.08
    94
    -0.08
     voc
    -0.07
    Gather
    -0.07
     veteran
    -0.07
     adopted
    -0.07
    POSITIVE LOGITS
     отверст
    0.08
     놓
    0.08
     редак
    0.08
    WAN
    0.07
    óstico
    0.07
    (inner
    0.07
     આય
    0.07
    Jos
    0.07
    óst
    0.07
    类型
    0.07
    Activations Density 0.007%

    No Known Activations