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. 15-RESID-POST-AA
    6. 19564
    Prev
    Next
    INDEX
    Explanations

    ingredient lists

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teatr
    -0.08
    (prompt
    -0.08
     optimizing
    -0.08
     Deadline
    -0.07
     Pandemic
    -0.07
     занятия
    -0.07
     shutting
    -0.07
    春节
    -0.07
     responding
    -0.07
     அன்று
    -0.07
    POSITIVE LOGITS
    -derived
    0.18
    -based
    0.12
     기반
    0.11
    -produced
    0.11
    浆
    0.10
    boy
    0.09
    -generated
    0.09
    ’huile
    0.09
     juice
    0.09
     आधारित
    0.09
    Activations Density 0.043%

    No Known Activations