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. 98484
    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
    =((
    -0.13
     ((
    -0.13
    ((&
    -0.12
     ulong
    -0.12
     (((
    -0.12
     uint
    -0.11
    (((
    -0.11
     ((((
    -0.11
    ((_
    -0.10
    ((-
    -0.10
    POSITIVE LOGITS
    ^)
    0.09
    #else
    0.08
    %)
    0.08
    *)"
    0.08
    <?↵
    0.08
    )application
    0.08
     '[
    0.08
     যা
    0.08
    #endif
    0.08
    (A
    0.08
    Activations Density 0.001%

    No Known Activations