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. 98374
    Prev
    Next
    INDEX
    Explanations

    say "MA" or "AV"

    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
    миш
    -0.08
    depends
    -0.08
     Pele
    -0.07
     blouse
    -0.07
    lower
    -0.07
    background
    -0.07
     Padre
    -0.07
    stackoverflow
    -0.07
    ுடைய
    -0.07
     שיה
    -0.07
    POSITIVE LOGITS
    AV
    0.18
    av
    0.18
     AV
    0.15
    avs
    0.13
     av
    0.13
    Av
    0.13
     Av
    0.12
    _av
    0.12
    (av
    0.12
    -av
    0.12
    Activations Density 0.001%

    No Known Activations