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. 66030
    Prev
    Next
    INDEX
    Explanations

    4

    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
    Accounting
    -0.09
     Mig
    -0.08
     evade
    -0.08
     Checks
    -0.08
    	Me
    -0.08
    utiny
    -0.07
     Accounting
    -0.07
     Fle
    -0.07
    zył
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    \,
    0.08
     கர
    0.08
     Arabian
    0.08
     ltd
    0.07
    ابة
    0.07
    <TResult
    0.07
     xxx
    0.07
     gardens
    0.07
    \\\\
    0.07
    .thumb
    0.07
    Activations Density 0.010%

    No Known Activations