© 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. 70877
    Prev
    Next
    INDEX
    Explanations

    code

    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
    協
    -0.09
     coop
    -0.08
     cooperative
    -0.08
     lumin
    -0.08
     Coop
    -0.08
     asym
    -0.08
    双色
    -0.08
     coopération
    -0.07
    充分
    -0.07
     koper
    -0.07
    POSITIVE LOGITS
    _CUR
    0.08
    949
    0.07
     பாட
    0.07
    chá
    0.07
     echoed
    0.07
    dirty
    0.07
    CUR
    0.07
    Phrase
    0.07
    입
    0.07
    	fire
    0.07
    Activations Density 0.080%

    No Known Activations