Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12000
    Prev
    Next
    INDEX
    Explanations

    iteration

    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
    怕
    -0.08
     Fra
    -0.07
    Gef
    -0.07
     हस्त
    -0.07
     bull
    -0.07
     distal
    -0.07
    138
    -0.07
     oral
    -0.07
    �
    -0.07
    hyd
    -0.07
    POSITIVE LOGITS
     bel
    0.08
     induc
    0.07
    HO
    0.07
     independ
    0.07
     dune
    0.07
     Jah
    0.07
     DSS
    0.07
     Everywhere
    0.07
     creep
    0.07
     sho
    0.07
    Activations Density 0.006%

    No Known Activations