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. 11-RESID-POST-AA
    6. 90192
    Prev
    Next
    INDEX
    Explanations

    Numbers in math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。同时
    -0.08
    ють
    -0.07
    arcely
    -0.07
    �니다
    -0.07
     لف
    -0.07
    Uploader
    -0.07
    ILLS
    -0.07
     порт
    -0.07
    。」
    -0.07
    าบ
    -0.07
    POSITIVE LOGITS
    ngx
    0.08
    [][]
    0.08
     sx
    0.08
    碰
    0.08
    width
    0.08
    hx
    0.07
    एका
    0.07
     <$>
    0.07
     nuggets
    0.07
    ેસ
    0.07
    Activations Density 0.076%

    No Known Activations