© 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. 44539
    Prev
    Next
    INDEX
    Explanations

    dominoes and board cutting

    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
    berge
    -0.08
     copia
    -0.08
     republican
    -0.08
    parte
    -0.08
    باره
    -0.08
     کپ
    -0.07
    meer
    -0.07
    plicht
    -0.07
    úp
    -0.07
     Genuine
    -0.07
    POSITIVE LOGITS
     mari
    0.08
     apparatuur
    0.08
     implied
    0.08
    zny
    0.07
    chem
    0.07
     Hamburger
    0.07
    Paused
    0.07
     нравится
    0.07
     autem
    0.07
     Ital
    0.07
    Activations Density 0.002%

    No Known Activations