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. 11-RESID-POST-AA
    6. 49129
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	DWORD
    -0.09
    DWORD
    -0.09
     rash
    -0.09
     occupational
    -0.08
     palindrome
    -0.08
     lagoon
    -0.08
     проник
    -0.08
     sheltered
    -0.08
     NAND
    -0.08
     griev
    -0.08
    POSITIVE LOGITS
     aesthetics
    0.16
     subplot
    0.14
    (figsize
    0.14
    subplot
    0.13
    (gca
    0.13
     aesthetic
    0.12
     xlabel
    0.12
    .savefig
    0.12
    xlabel
    0.12
     legends
    0.12
    Activations Density 0.012%

    No Known Activations