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. 46772
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Fen
    -0.08
     Pamp
    -0.08
     compét
    -0.08
     Kre
    -0.07
     климат
    -0.07
    適
    -0.07
     hennes
    -0.07
     glycol
    -0.07
    �
    -0.07
     Rh
    -0.07
    POSITIVE LOGITS
     mauris
    0.08
     समाचार
    0.08
    anything
    0.08
     seguito
    0.08
    ocity
    0.08
    DIY
    0.08
     Anything
    0.08
     babies
    0.08
    教程
    0.08
    ланып
    0.07
    Activations Density 0.012%

    No Known Activations