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. 98342
    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
    881
    -0.10
    08
    -0.10
    081
    -0.09
    884
    -0.09
    880
    -0.09
    875
    -0.09
    885
    -0.09
    福
    -0.08
    879
    -0.08
    882
    -0.08
    POSITIVE LOGITS
    817
    0.19
    790
    0.19
    789
    0.19
    818
    0.19
    810
    0.18
    791
    0.18
    814
    0.18
    823
    0.18
    82
    0.17
    811
    0.17
    Activations Density 0.089%

    No Known Activations