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. 130995
    Prev
    Next
    INDEX
    Explanations

    the letter "п"

    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
    િંગ
    -0.11
    িং
    -0.11
    ಿಂಗ್
    -0.10
    ਿੰਗ
    -0.10
    ్స
    -0.09
    ിങ്
    -0.09
    ామ్
    -0.09
    ിംഗ്
    -0.09
    ಬ್
    -0.09
    ਾਮ
    -0.09
    POSITIVE LOGITS
    роизвод
    0.09
    ம்ப
    0.09
    കട
    0.09
    ாய
    0.08
    роме
    0.08
     bete
    0.08
    оин
    0.08
    ánd
    0.08
    унк
    0.08
     Dhe
    0.08
    Activations Density 0.022%

    No Known Activations