Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 117553
    Prev
    Next
    INDEX
    Explanations

    simplifying fractions

    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
     HEX
    -0.07
     Alic
    -0.07
     Swedish
    -0.07
     Craw
    -0.07
    _wait
    -0.07
    HEX
    -0.07
    .Translate
    -0.07
    -0.07
     Hex
    -0.07
     sleek
    -0.07
    POSITIVE LOGITS
     стрем
    0.09
     ઘટાડ
    0.08
     aanleiding
    0.08
    -eff
    0.08
     sloppy
    0.08
     बराब
    0.08
    aneq
    0.08
     obvious
    0.08
     boleh
    0.08
     -->↵↵
    0.08
    Activations Density 0.015%

    No Known Activations