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. 53045
    Prev
    Next
    INDEX
    Explanations

    aware

    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
     planter
    -0.08
    ème
    -0.08
    rh
    -0.08
    self
    -0.07
    স্ট
    -0.07
     viš
    -0.07
    氣
    -0.07
    ő
    -0.07
    기가
    -0.07
    径
    -0.07
    POSITIVE LOGITS
     SEX
    0.09
     SIS
    0.08
     SNP
    0.08
     Singh
    0.08
     specialise
    0.08
     Sule
    0.08
     Secretaria
    0.08
     سیک
    0.08
     SIN
    0.08
     Securities
    0.08
    Activations Density 0.001%

    No Known Activations