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. 98123
    Prev
    Next
    INDEX
    Explanations

    字

    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
     Specifications
    -0.10
     specifications
    -0.09
    _specs
    -0.09
    Specifications
    -0.09
    _names
    -0.08
     specs
    -0.08
     بايد
    -0.08
     Sha
    -0.08
     推
    -0.07
     spé
    -0.07
    POSITIVE LOGITS
    乔
    0.08
    .tree
    0.08
     Right
    0.08
    冰
    0.07
     Ignite
    0.07
    .Animation
    0.07
     TREE
    0.07
     Pool
    0.07
    .grid
    0.07
    右
    0.07
    Activations Density 0.001%

    No Known Activations