© 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 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. 63551
    Prev
    Next
    INDEX
    Explanations

    phone

    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
    emies
    -0.08
     recr
    -0.08
    álise
    -0.08
     leveraging
    -0.08
    у
    -0.07
     biomechanics
    -0.07
    =true
    -0.07
     crystalline
    -0.07
     preservatives
    -0.07
    ulas
    -0.07
    POSITIVE LOGITS
     Unary
    0.09
     provincial
    0.08
    êng
    0.08
     전국
    0.08
     کب
    0.08
     Overseas
    0.08
     unary
    0.07
     stads
    0.07
    _IND
    0.07
     شهرستان
    0.07
    Activations Density 0.005%

    No Known Activations