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. 67734
    Prev
    Next
    INDEX
    Explanations

    fail

    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
     вмест
    -0.09
     øst
    -0.08
     дил
    -0.08
     bpy
    -0.08
     камер
    -0.08
     kän
    -0.08
     spiel
    -0.08
    小說
    -0.08
     профессион
    -0.08
    Interior
    -0.08
    POSITIVE LOGITS
     failures
    0.15
    失败
    0.15
     실패
    0.13
     failing
    0.13
     failure
    0.13
     fail
    0.13
    fail
    0.13
    _fail
    0.12
     Fail
    0.12
     fails
    0.12
    Activations Density 0.004%

    No Known Activations