© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108597
    Prev
    Next
    INDEX
    Explanations

    Shiva

    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
    «
    -0.08
     inflate
    -0.08
    -mentioned
    -0.08
     concerns
    -0.08
     aith
    -0.08
     inflated
    -0.07
    'affaires
    -0.07
     policym
    -0.07
     Synd
    -0.07
     concern
    -0.07
    POSITIVE LOGITS
     تعالى
    0.10
     พระ
    0.08
     dada
    0.08
     Mina
    0.08
     Vish
    0.07
     القض
    0.07
    finity
    0.07
     Trip
    0.07
    397
    0.07
    �
    0.07
    Activations Density 0.003%

    No Known Activations