© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111140
    Prev
    Next
    INDEX
    Explanations

    capital, working

    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
     multas
    -0.08
    ，公司
    -0.07
     importing
    -0.07
     hingga
    -0.07
     repairing
    -0.07
    Diagonal
    -0.07
     ersetzen
    -0.07
     depositing
    -0.07
    ELL
    -0.07
    bug
    -0.07
    POSITIVE LOGITS
    拥
    0.09
    _COMPLE
    0.08
    _FORCE
    0.08
     ux
    0.08
    unk
    0.08
     Determ
    0.08
    _FOR
    0.08
    ½
    0.08
    conde
    0.07
    astica
    0.07
    Activations Density 0.001%

    No Known Activations