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. 11-RESID-POST-AA
    6. 102802
    Prev
    Next
    INDEX
    Explanations

    attic

    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
     platelet
    -0.09
    ଶ
    -0.08
    Issuer
    -0.08
     savory
    -0.08
     пораж
    -0.07
    Plate
    -0.07
     manifesto
    -0.07
     receptor
    -0.07
     Patel
    -0.07
     Plate
    -0.07
    POSITIVE LOGITS
     attic
    0.12
    用品
    0.09
    阁
    0.09
     Thoughts
    0.08
    Songs
    0.08
     antics
    0.08
     coff
    0.08
     cottages
    0.08
    Kl
    0.08
     fugit
    0.08
    Activations Density 0.001%

    No Known Activations