© 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. 64558
    Prev
    Next
    INDEX
    Explanations

    approach

    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
    �
    -0.09
     merger
    -0.07
    -handler
    -0.07
    .kr
    -0.07
    -level
    -0.07
     teoria
    -0.07
    therapy
    -0.07
    -piece
    -0.07
    ít
    -0.07
     parties
    -0.07
    POSITIVE LOGITS
    なく
    0.08
    ATAR
    0.08
    sealed
    0.08
     waive
    0.08
     admir
    0.08
    faat
    0.08
     illumin
    0.08
    とか
    0.08
    、一
    0.07
     გაყ
    0.07
    Activations Density 0.484%

    No Known Activations