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. 119258
    Prev
    Next
    INDEX
    Explanations

    pad

    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
     laf
    -0.08
     Papua
    -0.08
    564
    -0.08
    045
    -0.08
     serm
    -0.07
     lur
    -0.07
     Fitch
    -0.07
     Erit
    -0.07
     Rab
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    uliar
    0.08
    (pre
    0.07
    (~
    0.07
     rinc
    0.07
     Render
    0.07
     teht
    0.07
     Hanson
    0.07
     Murray
    0.07
     cushioning
    0.07
     partic
    0.07
    Activations Density 0.008%

    No Known Activations