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. 111606
    Prev
    Next
    INDEX
    Explanations

    person

    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
    Subclass
    -0.09
     Compostela
    -0.08
     двор
    -0.07
     coste
    -0.07
     passenger
    -0.07
     Senhora
    -0.07
     reli
    -0.07
    故
    -0.07
    Distrito
    -0.07
    Xa
    -0.07
    POSITIVE LOGITS
     کارت
    0.08
     crunchy
    0.08
     ambiance
    0.07
     दिल
    0.07
     invaded
    0.07
    @endif
    0.07
    ił
    0.07
     ipin
    0.07
     للتح
    0.07
     força
    0.07
    Activations Density 0.002%

    No Known Activations