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. 43689
    Prev
    Next
    INDEX
    Explanations

    Python plotting 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
    308
    -0.08
    Jones
    -0.07
     calculates
    -0.07
    Coming
    -0.07
    Calculated
    -0.07
    -0.07
    Calculator
    -0.07
    152
    -0.07
    Descriptor
    -0.07
    Compute
    -0.07
    POSITIVE LOGITS
    .xlabel
    0.13
    .title
    0.12
     title
    0.11
     xlabel
    0.11
     제목
    0.11
     plt
    0.10
    (title
    0.10
     titulo
    0.10
    _xlabel
    0.10
    ,title
    0.10
    Activations Density 0.003%

    No Known Activations