© 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. 71030
    Prev
    Next
    INDEX
    Explanations

    Ar

    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
    edict
    -0.09
    :''
    -0.08
    =>'
    -0.08
    =>$
    -0.08
    eton
    -0.08
    олее
    -0.08
     funcion
    -0.08
     staten
    -0.08
     $__
    -0.08
    和平
    -0.08
    POSITIVE LOGITS
    ですね
    0.10
     
    0.09
    こんにちは
    0.09
    😊
    0.08
    さて
    0.08
    ครับ
    0.08
     
    0.08
    ज़र
    0.08
    燃
    0.08
    〈
    0.07
    Activations Density 0.171%

    No Known Activations