© 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. 11-RESID-POST-AA
    11. 47094
    Prev
    Next
    INDEX
    Explanations

    liquid

    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
     কর
    -0.07
    质
    -0.07
    -users
    -0.07
     meg
    -0.07
     мем
    -0.07
    mem
    -0.07
     pep
    -0.07
     привод
    -0.07
     sneak
    -0.07
     prema
    -0.07
    POSITIVE LOGITS
     arrêt
    0.08
    arbeitet
    0.08
     partida
    0.08
     arrêter
    0.08
    ైట్
    0.08
     Überg
    0.08
     Deux
    0.08
     علم
    0.08
    /plugin
    0.08
     Temps
    0.08
    Activations Density 0.001%

    No Known Activations