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. 74980
    Prev
    Next
    INDEX
    Explanations

    Perron-Frobenius theorem

    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
    ված
    -0.10
    ოსტ
    -0.09
     χω
    -0.08
     pali
    -0.08
     રહે
    -0.08
     रहे
    -0.08
    જૂ
    -0.08
     रहती
    -0.08
    ઓ
    -0.08
     komponent
    -0.08
    POSITIVE LOGITS
     herd
    0.08
     cartel
    0.08
     suele
    0.07
     recomendamos
    0.07
    .argmax
    0.07
     Simba
    0.07
    ုံ
    0.07
     monopol
    0.07
    ungu
    0.07
     dominant
    0.07
    Activations Density 0.001%

    No Known Activations