© 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. 48028
    Prev
    Next
    INDEX
    Explanations

    depiction

    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
     potassium
    -0.08
    prefix
    -0.08
    Equation
    -0.08
     durable
    -0.08
    priority
    -0.07
     Lil
    -0.07
     Pill
    -0.07
     Son
    -0.07
    양
    -0.07
    Pas
    -0.07
    POSITIVE LOGITS
    描
    0.09
     depicting
    0.09
     рис
    0.09
    ើ
    0.09
    /images
    0.09
    /movie
    0.08
      
    0.08
     scène
    0.08
     трав
    0.08
    บอลออนไลน์
    0.08
    Activations Density 0.005%

    No Known Activations