Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19534
    Prev
    Next
    INDEX
    Explanations

    +

    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
     obč
    -0.09
    zig
    -0.08
    (filename
    -0.08
     നട
    -0.08
    Merk
    -0.08
    (method
    -0.08
     შეგ
    -0.08
    ,(
    -0.08
    <label
    -0.08
     გამოყენ
    -0.08
    POSITIVE LOGITS
     eating
    0.09
     дополнитель
    0.08
     Eating
    0.08
    irse
    0.08
     ruok
    0.07
     drie
    0.07
    餐
    0.07
     sumar
    0.07
    삼
    0.07
     gastron
    0.07
    Activations Density 0.006%

    No Known Activations