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. 90834
    Prev
    Next
    INDEX
    Explanations

    standard, normally

    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
     greatly
    -0.08
     unlike
    -0.08
     Costume
    -0.07
     seat
    -0.07
    даем
    -0.07
     unconventional
    -0.07
     Kredit
    -0.07
     manufact
    -0.07
     kron
    -0.07
     significantly
    -0.07
    POSITIVE LOGITS
     GPT
    0.10
    <|start|>
    0.08
    <|end|>
    0.08
    /person
    0.08
    限制
    0.08
    annau
    0.08
     teko
    0.08
     Hello
    0.08
    GPT
    0.08
    Wikipedia
    0.08
    Activations Density 0.367%

    No Known Activations