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. 42136
    Prev
    Next
    INDEX
    Explanations

    Programming interfaces

    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
     masses
    -0.10
    ARGE
    -0.08
     آم
    -0.08
     admi
    -0.08
    Factors
    -0.08
     crush
    -0.08
    YSIS
    -0.08
     Scotch
    -0.08
    �
    -0.08
     hjælp
    -0.08
    POSITIVE LOGITS
    接口
    0.16
     интерф
    0.14
     interface
    0.14
     interfaz
    0.12
    interface
    0.12
    interfaces
    0.12
     Interface
    0.11
    .interface
    0.11
     IRepository
    0.11
     interfaces
    0.11
    Activations Density 0.013%

    No Known Activations