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. 78690
    Prev
    Next
    INDEX
    Explanations

    Avoiding the word "description"

    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
    wijs
    -0.08
     licences
    -0.08
     subsidi
    -0.08
     Lizenz
    -0.08
     ফের
    -0.08
     frying
    -0.08
     rech
    -0.08
    党委
    -0.07
     lice
    -0.07
    ыны
    -0.07
    POSITIVE LOGITS
     अंत
    0.08
     गर्द
    0.07
     depiction
    0.07
     embroidery
    0.07
     aesthetically
    0.07
    'or
    0.07
     portrays
    0.07
     वार
    0.07
     monoch
    0.07
    ात्मक
    0.07
    Activations Density 0.004%

    No Known Activations