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. 54245
    Prev
    Next
    INDEX
    Explanations

    own words

    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
    乘
    -0.08
    oraj
    -0.08
     opcion
    -0.07
     Adolf
    -0.07
     Modular
    -0.07
    েক্ষ
    -0.07
    ))->
    -0.07
     Ride
    -0.07
    理论
    -0.07
     Haar
    -0.07
    POSITIVE LOGITS
    ीत
    0.08
     הדברים
    0.08
     fatty
    0.08
     кет
    0.07
     pár
    0.07
     edilmiş
    0.07
    ровать
    0.07
     shades
    0.07
    own
    0.07
     elaborar
    0.07
    Activations Density 0.010%

    No Known Activations