© 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. 23-RESID-POST-AA
    11. 97637
    Prev
    Next
    INDEX
    Explanations

    eyes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иться
    -0.08
    Вес
    -0.08
    ится
    -0.08
    POSITION
    -0.08
     الجيش
    -0.08
    ляется
    -0.08
    $error
    -0.08
    position
    -0.08
    應
    -0.08
     takeaway
    -0.08
    POSITIVE LOGITS
    had
    0.14
    hadow
    0.13
    Had
    0.08
     aveva
    0.08
     had
    0.08
    acc
    0.08
     avait
    0.07
     Had
    0.07
     atua
    0.07
    elia
    0.07
    Activations Density 0.001%

    No Known Activations