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. 13041
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
     Zoom
    -0.08
     Dram
    -0.07
    .”
    -0.07
     increase
    -0.07
     Garmin
    -0.07
    _activity
    -0.07
     Hammond
    -0.07
     zehn
    -0.07
    VIII
    -0.07
    تان
    -0.07
    POSITIVE LOGITS
    ീസ്
    0.10
     pragma
    0.08
    ғ
    0.08
    кту
    0.08
    인트
    0.08
    mmat
    0.07
    ਮੇ
    0.07
    ദേശ
    0.07
     thermo
    0.07
    береж
    0.07
    Activations Density 0.046%

    No Known Activations