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. 65651
    Prev
    Next
    INDEX
    Explanations

    yeast

    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
     divisor
    -0.09
     Residential
    -0.09
    Residential
    -0.09
     receptive
    -0.08
    rence
    -0.08
     lecture
    -0.08
     crumble
    -0.08
     residential
    -0.08
     vigente
    -0.08
     lectures
    -0.08
    POSITIVE LOGITS
     yeast
    0.11
     Eurovision
    0.09
     Portug
    0.08
    Liqu
    0.08
     braid
    0.08
    葡
    0.08
     Liqu
    0.08
     гриб
    0.08
     wines
    0.08
    ulong
    0.08
    Activations Density 0.003%

    No Known Activations