Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 75975
    Prev
    Next
    INDEX
    Explanations

    fears and phobias

    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
    setter
    -0.08
    tionen
    -0.08
     trưởng
    -0.08
    iqué
    -0.08
     adip
    -0.08
     distributing
    -0.08
    Trim
    -0.08
     الأمة
    -0.08
     steadily
    -0.08
    Cargo
    -0.08
    POSITIVE LOGITS
    怖
    0.19
     डर
    0.18
     horror
    0.17
     भय
    0.17
     fears
    0.16
     fear
    0.16
     assust
    0.16
     fearful
    0.16
     scared
    0.16
     scary
    0.16
    Activations Density 0.068%

    No Known Activations