© 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. 77944
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    Sono
    -0.08
    Supervisor
    -0.08
    Because
    -0.08
    Lorem
    -0.08
    CALE
    -0.08
     Gide
    -0.08
    (@
    -0.08
     cái
    -0.07
    Basically
    -0.07
    ுகிறார்
    -0.07
    POSITIVE LOGITS
    �
    0.08
     Vertrags
    0.08
     Pollution
    0.08
    dda
    0.08
     Salvation
    0.07
    _swap
    0.07
     चुकी
    0.07
     Curse
    0.07
     wieku
    0.07
    ocolate
    0.07
    Activations Density 0.175%

    No Known Activations