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. 98514
    Prev
    Next
    INDEX
    Explanations

    �

    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
    #
    -0.10
     Nee
    -0.09
    _NS
    -0.09
    _\
    -0.09
     NS
    -0.09
    (NS
    -0.08
    Myanmar
    -0.08
     "#
    -0.07
    #
    ↵
    -0.07
    _{\
    -0.07
    POSITIVE LOGITS
    n
    0.35
    �
    0.26
    partial
    0.24
     partial
    0.20
     Partial
    0.18
    náv
    0.18
    .partial
    0.18
    Partial
    0.17
     n
    0.17
    �
    0.17
    Activations Density 0.029%

    No Known Activations