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. 59011
    Prev
    Next
    INDEX
    Explanations

    word 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
    ર્મ
    -0.08
     Alemanha
    -0.08
     Waterfront
    -0.08
     altura
    -0.08
     ક
    -0.08
    irms
    -0.08
    主体
    -0.08
     నవ
    -0.08
     França
    -0.08
    leder
    -0.08
    POSITIVE LOGITS
    (i
    0.08
     Suppose
    0.08
    (Position
    0.08
    Supp
    0.08
     ammon
    0.07
    IPLE
    0.07
    (pos
    0.07
    (a
    0.07
    (ii
    0.07
     unscr
    0.07
    Activations Density 0.400%

    No Known Activations