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. 119355
    Prev
    Next
    INDEX
    Explanations

    2

    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
    同性
    -0.08
     dann
    -0.08
     gode
    -0.07
     cor
    -0.07
     corpos
    -0.07
     কর
    -0.07
    ldre
    -0.07
     mower
    -0.07
     chatter
    -0.07
     slutt
    -0.07
    POSITIVE LOGITS
     gusto
    0.09
     जन
    0.08
    ieg
    0.08
     Target
    0.08
     Hosted
    0.07
     Default
    0.07
     Static
    0.07
     Strategy
    0.07
    ไม
    0.07
    戰
    0.07
    Activations Density 0.021%

    No Known Activations