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. 102929
    Prev
    Next
    INDEX
    Explanations

    YAML

    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
    ookies
    -0.08
     muscle
    -0.08
     epithelial
    -0.08
    ίζ
    -0.08
     roam
    -0.08
     roaming
    -0.08
     glamour
    -0.08
     glamorous
    -0.07
    赚
    -0.07
     Sony
    -0.07
    POSITIVE LOGITS
     YAML
    0.17
    Yaml
    0.16
    _yaml
    0.16
     yaml
    0.16
    yaml
    0.16
    .yaml
    0.15
    .yml
    0.14
     Helm
    0.10
     unmar
    0.08
    Dok
    0.08
    Activations Density 0.004%

    No Known Activations