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. 42107
    Prev
    Next
    INDEX
    Explanations

    n

    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
     overseas
    -0.08
     vues
    -0.08
    ర్ట
    -0.08
     рас
    -0.07
    енз
    -0.07
     ク
    -0.07
     просмот
    -0.07
    алай
    -0.07
    Skill
    -0.07
    .elastic
    -0.07
    POSITIVE LOGITS
     Bartlett
    0.08
     CHAR
    0.08
    तील
    0.08
    ")(
    0.07
    ישי
    0.07
     पी
    0.07
     factorial
    0.07
    _next
    0.07
    वर
    0.07
    강
    0.07
    Activations Density 0.019%

    No Known Activations