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. 88255
    Prev
    Next
    INDEX
    Explanations

    landscape and aspect ratio

    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
    ocket
    -0.08
     populations
    -0.08
    (pop
    -0.07
    .paths
    -0.07
    NS
    -0.07
    (integer
    -0.07
     Miser
    -0.07
     recursively
    -0.07
    pts
    -0.07
    etermined
    -0.07
    POSITIVE LOGITS
     ngang
    0.09
    -talet
    0.09
     horizontal
    0.09
     agrad
    0.09
     agradable
    0.09
    horizontal
    0.08
    _HORIZONTAL
    0.08
     sacrificed
    0.08
     Smash
    0.08
     ahi
    0.08
    Activations Density 0.012%

    No Known Activations