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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113081
    Prev
    Next
    INDEX
    Explanations

    9

    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
    حاس
    -0.08
     artifacts
    -0.08
     arte
    -0.08
     evidence
    -0.07
    jud
    -0.07
     evid
    -0.07
     Sofa
    -0.07
     कस
    -0.07
    gesetzt
    -0.07
     simplest
    -0.07
    POSITIVE LOGITS
     strchr
    0.09
     avail
    0.08
    יבור
    0.08
     count
    0.08
    exclude
    0.08
    -count
    0.08
     Distr
    0.08
    /count
    0.08
     autonomy
    0.08
     మొత్తం
    0.08
    Activations Density 0.018%

    No Known Activations