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. 49311
    Prev
    Next
    INDEX
    Explanations

    stuffed

    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
     combust
    -0.09
     eben
    -0.08
     IIS
    -0.08
    Committed
    -0.08
     yolu
    -0.08
     offshore
    -0.08
     asm
    -0.08
     anod
    -0.08
     accelerating
    -0.08
    一期
    -0.08
    POSITIVE LOGITS
     teddy
    0.12
     игруш
    0.11
    娃
    0.11
     dolls
    0.11
     plush
    0.11
     toys
    0.11
     cudd
    0.10
    Replica
    0.10
     Replica
    0.09
     suitcase
    0.09
    Activations Density 0.021%

    No Known Activations