Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99108
    Prev
    Next
    INDEX
    Explanations

    Lucas

    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
    hme
    -0.08
    eem
    -0.08
    mallow
    -0.08
     workflow
    -0.08
     pé
    -0.08
     shoreline
    -0.08
    woman
    -0.08
     submerged
    -0.08
    hour
    -0.08
    晚上
    -0.07
    POSITIVE LOGITS
     anal
    0.08
     obdob
    0.08
    된다
    0.08
     Oficial
    0.08
     Ethereum
    0.08
     analogue
    0.08
     Anal
    0.08
     analog
    0.08
    됐다
    0.08
     analogy
    0.08
    Activations Density 0.002%

    No Known Activations