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. 58226
    Prev
    Next
    INDEX
    Explanations

    00

    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
     והת
    -0.09
     מוע
    -0.08
    BREAK
    -0.08
     Experienced
    -0.08
     העל
    -0.07
     marquee
    -0.07
    Experienced
    -0.07
    iders
    -0.07
     pergunt
    -0.07
    blockquote
    -0.07
    POSITIVE LOGITS
    स्या
    0.08
     मतलब
    0.08
    koh
    0.08
    969
    0.08
    kun
    0.07
    厨房
    0.07
     يعني
    0.07
    حم
    0.07
     cucina
    0.07
     osoby
    0.07
    Activations Density 0.001%

    No Known Activations