Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30630
    Prev
    Next
    INDEX
    Explanations

    artistic descriptions

    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
     нескольких
    -0.08
     SQL
    -0.08
     превыш
    -0.08
     настав
    -0.08
     норм
    -0.08
     наруш
    -0.08
     проис
    -0.08
     доказ
    -0.08
    _norm
    -0.08
    _SQL
    -0.08
    POSITIVE LOGITS
     effortlessly
    0.08
     Estudos
    0.08
    டிய
    0.07
     Lola
    0.07
    一样
    0.07
     clav
    0.07
     Vaak
    0.07
     Madeleine
    0.07
     Eerste
    0.07
     Municipal
    0.07
    Activations Density 0.079%

    No Known Activations