© 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. 94413
    Prev
    Next
    INDEX
    Explanations

    platform

    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
     Hag
    -0.08
    Kr
    -0.08
    rs
    -0.08
     anteced
    -0.07
    余
    -0.07
     prognosis
    -0.07
    erven
    -0.07
     Kraken
    -0.07
    274
    -0.07
    774
    -0.07
    POSITIVE LOGITS
     apr
    0.08
     Kah
    0.08
     sch
    0.08
     ni
    0.08
    平台
    0.07
     sm
    0.07
     platforms
    0.07
     رو
    0.07
    _owner
    0.07
    -platform
    0.07
    Activations Density 0.017%

    No Known Activations