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. 23-RESID-POST-AA
    6. 130961
    Prev
    Next
    INDEX
    Explanations

    cars and trains

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Damage
    -0.10
    Damage
    -0.10
     damage
    -0.10
     cadáver
    -0.10
     피해
    -0.09
     disturbances
    -0.09
    problem
    -0.09
     casualties
    -0.09
     daño
    -0.09
     Schäden
    -0.09
    POSITIVE LOGITS
     boating
    0.13
     car
    0.13
     bus
    0.12
    _train
    0.12
    .train
    0.11
    .car
    0.11
     ट्रेन
    0.11
     train
    0.11
     workplace
    0.11
    _car
    0.11
    Activations Density 0.016%

    No Known Activations