© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1490
    Prev
    Next
    INDEX
    Explanations

    split

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vital
    -0.08
    /ap
    -0.07
     MUT
    -0.07
     бі
    -0.07
    ांचा
    -0.07
     earth
    -0.07
    _once
    -0.07
     cartilage
    -0.07
    essential
    -0.07
    -0.07
    POSITIVE LOGITS
     متفاوت
    0.08
     Routes
    0.08
     nous
    0.08
     sorprender
    0.08
    icious
    0.08
     atrap
    0.08
     لحاظ
    0.08
     disple
    0.08
     Fernández
    0.08
     début
    0.08
    Activations Density 0.007%
    No Known Activations