© 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. 11-RESID-POST-AA
    11. 79465
    Prev
    Next
    INDEX
    Explanations

    Equals signs

    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
     timestep
    -0.08
    Inst
    -0.08
     Inst
    -0.08
    206
    -0.07
     HR
    -0.07
     postcode
    -0.07
     installation
    -0.07
     HPC
    -0.07
     INSTALL
    -0.07
     fibres
    -0.07
    POSITIVE LOGITS
     simultaneously
    0.10
     одновременно
    0.09
     simultaneous
    0.09
     동시에
    0.09
    _chain
    0.09
    barra
    0.08
     irresist
    0.08
     chain
    0.08
     각각
    0.08
    ász
    0.08
    Activations Density 0.028%

    No Known Activations