© 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. 45634
    Prev
    Next
    INDEX
    Explanations

    flex

    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
    、一
    -0.08
    óst
    -0.08
    、多
    -0.08
    yet
    -0.08
    dı
    -0.07
    Ignoring
    -0.07
    _Move
    -0.07
    -0.07
    -inc
    -0.07
     новости
    -0.07
    POSITIVE LOGITS
    际
    0.09
    оспособ
    0.08
    בית
    0.08
    -items
    0.08
     laborum
    0.08
    ateau
    0.08
     Anthony
    0.08
     occaec
    0.07
    werken
    0.07
     auff
    0.07
    Activations Density 0.001%
    No Known Activations