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. 130862
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     statistics
    -0.09
    _tile
    -0.09
     Creed
    -0.08
    _flags
    -0.08
    لفة
    -0.08
     Statistics
    -0.08
    štine
    -0.08
    _fixture
    -0.08
    Tile
    -0.08
     tile
    -0.08
    POSITIVE LOGITS
    152
    0.22
    052
    0.17
    952
    0.17
    752
    0.17
    652
    0.17
    452
    0.16
    552
    0.15
    352
    0.15
    852
    0.13
    52
    0.13
    Activations Density 0.022%

    No Known Activations