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. 23-RESID-POST-AA
    6. 98040
    Prev
    Next
    INDEX
    Explanations

    medical/biological terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istente
    -0.08
    /us
    -0.08
     manej
    -0.08
     editable
    -0.08
    edig
    -0.08
    iclop
    -0.08
    ованный
    -0.08
     ৰূপ
    -0.08
    -informed
    -0.08
    ked
    -0.08
    POSITIVE LOGITS
     muscular
    0.09
    vascular
    0.08
    ärer
    0.08
    estinal
    0.08
     adquirir
    0.08
    ériel
    0.08
     сосуд
    0.08
    äss
    0.08
    imali
    0.07
     endothelial
    0.07
    Activations Density 0.007%

    No Known Activations