© 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. 29278
    Prev
    Next
    INDEX
    Explanations

    equals

    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
     exclusion
    -0.08
     exclusions
    -0.07
     excludes
    -0.07
    XV
    -0.07
     inner
    -0.07
    ]interface
    -0.07
     group's
    -0.06
    TEGR
    -0.06
     faits
    -0.06
    cout
    -0.06
    POSITIVE LOGITS
     COPYRIGHT
    0.09
     соответственно
    0.09
     Dash
    0.09
    东北
    0.08
     SAMPLE
    0.08
     Esto
    0.08
     neist
    0.08
    Connor
    0.08
     Russie
    0.08
    Dash
    0.08
    Activations Density 0.072%

    No Known Activations