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. 98611
    Prev
    Next
    INDEX
    Explanations

    say ".get"

    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
     GET
    -0.13
    _Set
    -0.13
    :Set
    -0.12
     setter
    -0.12
    _Get
    -0.12
     setters
    -0.12
    GET
    -0.12
    .GET
    -0.12
    :set
    -0.11
    (Get
    -0.11
    POSITIVE LOGITS
     ge
    0.14
    ge
    0.11
     ге
    0.11
    .ge
    0.11
    Ge
    0.10
     gé
    0.10
     Ge
    0.09
    .Ge
    0.09
     את
    0.09
    의
    0.09
    Activations Density 0.004%

    No Known Activations