Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19134
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viene
    -0.09
     come
    -0.09
    fore
    -0.08
    >>()
    -0.08
    ly
    -0.08
     comes
    -0.08
     consensus
    -0.08
     coming
    -0.08
     entails
    -0.07
     other
    -0.07
    POSITIVE LOGITS
    ("",
    0.23
    (",",
    0.21
    ('',
    0.20
    (".",
    0.19
    (',',
    0.19
    ('.',
    0.19
    ([],
    0.18
    ({},
    0.18
    ("/",
    0.17
    ('/',
    0.17
    Activations Density 0.029%

    No Known Activations