© 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. 31157
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
     movements
    -0.08
     pertes
    -0.07
    екции
    -0.07
     adaptation
    -0.07
    Sw
    -0.07
     amak
    -0.07
     cities
    -0.07
    ুস
    -0.07
     movement
    -0.07
     mouvements
    -0.07
    POSITIVE LOGITS
     Exclus
    0.11
     exclusivos
    0.10
     exclus
    0.09
     Rather
    0.09
     EXACT
    0.09
     Exclusive
    0.09
     exclusivamente
    0.09
    exclusive
    0.08
     Exactly
    0.08
     Intermediate
    0.08
    Activations Density 0.097%

    No Known Activations