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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1339
    Prev
    Next
    INDEX
    Explanations

    property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    দ্ধ
    -0.07
     বির
    -0.07
     মনে
    -0.07
     pensar
    -0.07
    梁
    -0.07
    ិប
    -0.07
     obstacle
    -0.07
    precedented
    -0.07
          
    -0.07
    failure
    -0.07
    POSITIVE LOGITS
     金
    0.09
     bytes
    0.08
     gull
    0.07
     PCA
    0.07
     bà
    0.07
    .money
    0.07
     permitted
    0.07
     possessed
    0.07
    Capabilities
    0.07
    akw
    0.07
    Activations Density 0.000%

    No Known Activations