© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48828
    Prev
    Next
    INDEX
    Explanations

    Persian prepositions

    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
    now
    -0.10
    آپ
    -0.09
     and
    -0.09
    лі
    -0.09
    ्ड
    -0.09
    ਟ
    -0.09
    ٹھ
    -0.08
    -assisted
    -0.08
    ल
    -0.08
    Ly
    -0.08
    POSITIVE LOGITS
     برای
    0.26
     از
    0.26
     در
    0.25
     به
    0.24
     با
    0.24
     علاوه
    0.21
     باعث
    0.21
     توسط
    0.19
     درباره
    0.19
     بنابراین
    0.19
    Activations Density 0.018%

    No Known Activations