© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103259
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outputs
    -0.08
    Desired
    -0.08
     =
    -0.07
     Output
    -0.07
    Output
    -0.07
    Outputs
    -0.07
    [class
    -0.07
     Outputs
    -0.07
    outputs
    -0.07
     Desired
    -0.07
    POSITIVE LOGITS
     વિશે
    0.15
     बारे
    0.15
    关于
    0.15
     గురించి
    0.14
    about
    0.14
     tungkol
    0.14
     ngeunaan
    0.14
     关于
    0.14
     it's
    0.14
     hakkında
    0.14
    Activations Density 0.005%

    No Known Activations