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. 98636
    Prev
    Next
    INDEX
    Explanations

    say "2"

    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
     دوه
    -0.14
     twice
    -0.12
     दुई
    -0.12
     Deux
    -0.12
     Twice
    -0.12
     ике
    -0.12
     kaks
    -0.11
     દ્વ
    -0.11
     აღნიშნა
    -0.11
     แกรม
    -0.11
    POSITIVE LOGITS
    �
    0.09
    182
    0.08
     связано
    0.07
    147
    0.07
    ombr
    0.07
    27
    0.07
    232
    0.07
     recul
    0.06
    ీ
    0.06
    ಲ
    0.06
    Activations Density 0.620%

    No Known Activations