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. 120234
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     संघ
    -0.08
     follow
    -0.08
     zählen
    -0.07
    :Set
    -0.07
     लक्ष्य
    -0.07
    (IN
    -0.07
     cuad
    -0.07
    rene
    -0.07
     rotate
    -0.07
    stance
    -0.07
    POSITIVE LOGITS
    nog
    0.08
     wi
    0.08
    是什么意思
    0.08
    дал
    0.08
    나
    0.07
    жі
    0.07
    عديد
    0.07
     어
    0.07
    жди
    0.07
    25
    0.07
    Activations Density 0.034%

    No Known Activations