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. 15-RESID-POST-AA
    6. 112
    Prev
    Next
    INDEX
    Explanations

    Explaining a concept comprehensively

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Either
    -0.09
    ибо
    -0.09
    Особ
    -0.08
    Either
    -0.08
     Desire
    -0.08
     nějak
    -0.08
     ’’
    -0.08
     muaj
    -0.08
     bestselling
    -0.08
     hòa
    -0.08
    POSITIVE LOGITS
    /R
    0.09
     &
    0.09
    ↵↵↵↵
    0.08
     vs
    0.08
    /
    0.08
    .RO
    0.08
    -s
    0.08
    -de
    0.08
    =self
    0.07
    、
    0.07
    Activations Density 0.045%

    No Known Activations