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. 52916
    Prev
    Next
    INDEX
    Explanations

    Benedict

    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
    ounter
    -0.08
    .attr
    -0.08
    ೊಂದ
    -0.07
     referido
    -0.07
     refers
    -0.07
     де
    -0.07
    coupon
    -0.07
    CR
    -0.07
     stats
    -0.07
    .short
    -0.07
    POSITIVE LOGITS
    ’avait
    0.09
     Itali
    0.09
    itar
    0.09
     כש
    0.08
     китап
    0.08
     ספר
    0.08
     Dhabi
    0.08
     gbogbo
    0.08
     rocky
    0.08
    idän
    0.08
    Activations Density 0.001%

    No Known Activations