© 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. 94621
    Prev
    Next
    INDEX
    Explanations

    |

    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
    uintptr
    -0.08
    intern
    -0.08
    .pipe
    -0.08
    Craig
    -0.08
     intern
    -0.07
    CRC
    -0.07
     ambit
    -0.07
    Reads
    -0.07
    。
    -0.07
    .Controller
    -0.07
    POSITIVE LOGITS
    amiseks
    0.09
     الثلاث
    0.08
     Infiniti
    0.08
     Bedarf
    0.08
     техники
    0.08
     kuni
    0.08
     jd
    0.08
     бояд
    0.07
    ouss
    0.07
     dre
    0.07
    Activations Density 0.010%

    No Known Activations