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. 98475
    Prev
    Next
    INDEX
    Explanations

    Hungarian programming contexts

    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
    ത്തിന
    -0.09
    itos
    -0.09
    ицу
    -0.09
    prisingly
    -0.08
    ənd
    -0.08
    ندی
    -0.08
     ہوگ
    -0.08
    �
    -0.08
    owy
    -0.08
    ிக்கு
    -0.08
    POSITIVE LOGITS
    usan
    0.16
    ail
    0.13
    uss
    0.11
    us
    0.11
    ai
    0.10
    usk
    0.10
    ust
    0.09
    usr
    0.09
    SAN
    0.08
     usa
    0.08
    Activations Density 0.001%

    No Known Activations