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. 12719
    Prev
    Next
    INDEX
    Explanations

    code

    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
     washed
    -0.08
     else
    -0.07
     recruited
    -0.07
    .vars
    -0.07
    招生
    -0.07
     harjo
    -0.07
     merchandising
    -0.07
    (isset
    -0.07
    Selective
    -0.07
    (nums
    -0.07
    POSITIVE LOGITS
     printable
    0.09
     Printable
    0.09
     génér
    0.09
     YAML
    0.09
     textual
    0.08
    mdi
    0.08
     latex
    0.08
     Mermaid
    0.08
     Viewer
    0.08
    生成
    0.08
    Activations Density 0.008%

    No Known Activations