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. 13030
    Prev
    Next
    INDEX
    Explanations

    subjective

    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
    (di
    -0.09
     unexpected
    -0.08
    .poly
    -0.08
     Ami
    -0.07
    -neck
    -0.07
     Clinton
    -0.07
    .named
    -0.07
    -0.07
    Unexpected
    -0.07
    Spread
    -0.07
    POSITIVE LOGITS
     subjective
    0.11
     subjet
    0.09
     percepción
    0.09
     subjekt
    0.09
     opinions
    0.09
     perception
    0.09
    意见
    0.09
     perceptions
    0.08
     ощущ
    0.08
     субъ
    0.08
    Activations Density 0.003%

    No Known Activations