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. 15-RESID-POST-AA
    6. 18950
    Prev
    Next
    INDEX
    Explanations

    Cash/bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दी
    -0.08
     senza
    -0.07
    Sizing
    -0.07
     стимули
    -0.07
     PARAM
    -0.07
    IGIN
    -0.07
     రూపొంద
    -0.07
     safeguards
    -0.07
     समर्थन
    -0.07
    Parameterized
    -0.07
    POSITIVE LOGITS
    832
    0.08
     rob
    0.08
    /email
    0.08
    606
    0.07
     snorkeling
    0.07
    396
    0.07
     synagogue
    0.07
     robbed
    0.07
    /github
    0.07
     substituted
    0.07
    Activations Density 0.002%

    No Known Activations