© 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. 97579
    Prev
    Next
    INDEX
    Explanations

    ré

    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
    ализ
    -0.09
    unis
    -0.08
     part
    -0.08
     ORM
    -0.08
    alis
    -0.08
     اللي
    -0.08
    responses
    -0.07
     Putting
    -0.07
     :::::
    -0.07
    Responses
    -0.07
    POSITIVE LOGITS
    tention
    0.16
    tabl
    0.10
    curr
    0.10
    clamation
    0.10
     संस्करण
    0.09
    plique
    0.09
    (curr
    0.08
     curr
    0.08
    版本
    0.08
    acağını
    0.08
    Activations Density 0.001%

    No Known Activations