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. 9117
    Prev
    Next
    INDEX
    Explanations

    @(

    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
    coffee
    -0.08
     Text
    -0.08
     Command
    -0.08
    uggest
    -0.07
    .command
    -0.07
    889
    -0.07
    _command
    -0.07
    	Command
    -0.07
    оти
    -0.07
    Rounded
    -0.07
    POSITIVE LOGITS
     sake
    0.08
    ONTAL
    0.08
    WORLD
    0.08
     मध्य
    0.08
    ্�
    0.07
     diri
    0.07
     रव
    0.07
     monna
    0.07
     ممت
    0.07
     שער
    0.07
    Activations Density 0.000%

    No Known Activations