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. 76270
    Prev
    Next
    INDEX
    Explanations

    layering

    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
     fleet
    -0.07
    rtc
    -0.07
    302
    -0.07
     મળે
    -0.07
     type
    -0.07
    NY
    -0.07
    GET
    -0.07
    Intel
    -0.07
     შესაბამისად
    -0.07
     timer
    -0.07
    POSITIVE LOGITS
     layering
    0.15
     �
    0.14
     Layer
    0.14
     capas
    0.14
     Layers
    0.14
     layers
    0.13
    -layer
    0.13
    _layer
    0.13
    _LAYER
    0.12
    _layers
    0.12
    Activations Density 0.022%

    No Known Activations