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. 15-RESID-POST-AA
    6. 160
    Prev
    Next
    INDEX
    Explanations

    all

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suffisamment
    -0.09
     readily
    -0.08
     genügend
    -0.08
     கலந்து
    -0.08
     relativement
    -0.08
     merely
    -0.08
     Lour
    -0.08
    ුවන්
    -0.07
     beschikken
    -0.07
     utilis
    -0.07
    POSITIVE LOGITS
     предыдущ
    0.09
     кроме
    0.09
     ಹಿಂದ
    0.08
     excepto
    0.08
     behalve
    0.08
    _except
    0.08
     السابقة
    0.08
     previous
    0.08
    ↑
    0.08
    _prior
    0.08
    Activations Density 0.018%

    No Known Activations