© 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. 65379
    Prev
    Next
    INDEX
    Explanations

    cylindrical tank volume calculation

    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
    .K
    -0.09
    .global
    -0.08
    .k
    -0.08
    (global
    -0.08
     정보
    -0.07
    	k
    -0.07
    >K
    -0.07
     연결
    -0.07
    *k
    -0.07
    (const
    -0.07
    POSITIVE LOGITS
     вода
    0.09
    beaut
    0.08
     quelle
    0.08
     Fight
    0.08
     hardest
    0.08
     скоро
    0.08
     aplicação
    0.08
     moments
    0.08
     rano
    0.07
    
    0.07
    Activations Density 0.007%

    No Known Activations