© 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. 64360
    Prev
    Next
    INDEX
    Explanations

    counting circle

    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
    优化
    -0.08
     HDR
    -0.08
     DOI
    -0.07
     holog
    -0.07
     DOE
    -0.07
     grounding
    -0.07
     dipl
    -0.07
     selten
    -0.07
     avenues
    -0.07
    .Scope
    -0.07
    POSITIVE LOGITS
     extermin
    0.10
     eliminación
    0.10
     survivors
    0.09
    淘
    0.09
     survivor
    0.09
     হত্যা
    0.09
     elimination
    0.09
     remov
    0.09
     negras
    0.09
     repeatedly
    0.09
    Activations Density 0.017%

    No Known Activations